ai to search for research papers

A free, AI-powered research tool for scientific literature

• Alice Kessler-Harris
• Multiple Sclerosis
• Economic Growth

New & Improved API for Developers

Introducing semantic reader in beta.

Stay Connected With Semantic Scholar Sign Up What Is Semantic Scholar? Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.

Analyze research papers at superhuman speed

Search for research papers, get one sentence abstract summaries, select relevant papers and search for more like them, extract details from papers into an organized table.

Find themes and concepts across many papers

Don't just take our word for it.

Tons of features to speed up your research

Upload your own pdfs, orient with a quick summary, view sources for every answer, ask questions to papers, research for the machine intelligence age, pick a plan that's right for you, get in touch, enterprise and institutions, custom pricing, common questions. great answers., how do researchers use elicit.

Over 2 million researchers have used Elicit. Researchers commonly use Elicit to:

• Speed up literature review
• Find papers they couldn’t find elsewhere
• Automate systematic reviews and meta-analyses
• Learn about a new domain

Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning.

What is Elicit not a good fit for?

Elicit does not currently answer questions or surface information that is not written about in an academic paper. It tends to work less well for identifying facts (e.g. “How many cars were sold in Malaysia last year?”) and theoretical or non-empirical domains.

What types of data can Elicit search over?

Elicit searches across 125 million academic papers from the Semantic Scholar corpus, which covers all academic disciplines. When you extract data from papers in Elicit, Elicit will use the full text if available or the abstract if not.

How accurate are the answers in Elicit?

A good rule of thumb is to assume that around 90% of the information you see in Elicit is accurate. While we do our best to increase accuracy without skyrocketing costs, it’s very important for you to check the work in Elicit closely. We try to make this easier for you by identifying all of the sources for information generated with language models.

What is Elicit Plus?

Elicit Plus is Elicit's subscription offering, which comes with a set of features, as well as monthly credits. On Elicit Plus, you may use up to 12,000 credits a month. Unused monthly credits do not carry forward into the next month. Plus subscriptions auto-renew every month.

What are credits?

Elicit uses a credit system to pay for the costs of running our app. When you run workflows and add columns to tables it will cost you credits. When you sign up you get 5,000 credits to use. Once those run out, you'll need to subscribe to Elicit Plus to get more. Credits are non-transferable.

How can you get in contact with the team?

Please email us at [email protected] or post in our Slack community if you have feedback or general comments! We log and incorporate all user comments. If you have a problem, please email [email protected] and we will try to help you as soon as possible.

What happens to papers uploaded to Elicit?

When you upload papers to analyze in Elicit, those papers will remain private to you and will not be shared with anyone else.

How accurate is Elicit?

Training our models on specific tasks, searching over academic papers, making it easy to double-check answers, save time, think more. try elicit for free..

The best AI tools for research papers and academic research (Literature review, grants, PDFs and more)

As our collective understanding and application of artificial intelligence (AI) continues to evolve, so too does the realm of academic research. Some people are scared by it while others are openly embracing the change. 

Make no mistake, AI is here to stay!

Instead of tirelessly scrolling through hundreds of PDFs, a powerful AI tool comes to your rescue, summarizing key information in your research papers. Instead of manually combing through citations and conducting literature reviews, an AI research assistant proficiently handles these tasks.

These aren’t futuristic dreams, but today’s reality. Welcome to the transformative world of AI-powered research tools!

This blog post will dive deeper into these tools, providing a detailed review of how AI is revolutionizing academic research. We’ll look at the tools that can make your literature review process less tedious, your search for relevant papers more precise, and your overall research process more efficient and fruitful.

I know that I wish these were around during my time in academia. It can be quite confronting when trying to work out what ones you should and shouldn’t use. A new one seems to be coming out every day!

Here is everything you need to know about AI for academic research and the ones I have personally trialed on my YouTube channel.

My Top AI Tools for Researchers and Academics – Tested and Reviewed!

There are many different tools now available on the market but there are only a handful that are specifically designed with researchers and academics as their primary user.

These are my recommendations that’ll cover almost everything that you’ll want to do:

Want to find out all of the tools that you could use?

Here they are, below:

AI literature search and mapping – best AI tools for a literature review – elicit and more

Harnessing AI tools for literature reviews and mapping brings a new level of efficiency and precision to academic research. No longer do you have to spend hours looking in obscure research databases to find what you need!

AI-powered tools like Semantic Scholar and elicit.org use sophisticated search engines to quickly identify relevant papers.

They can mine key information from countless PDFs, drastically reducing research time. You can even search with semantic questions, rather than having to deal with key words etc.

With AI as your research assistant, you can navigate the vast sea of scientific research with ease, uncovering citations and focusing on academic writing. It’s a revolutionary way to take on literature reviews.

• Elicit –  https://elicit.org
• Litmaps –  https://www.litmaps.com
• Research rabbit – https://www.researchrabbit.ai/
• Connected Papers –  https://www.connectedpapers.com/
• Supersymmetry.ai: https://www.supersymmetry.ai
• Semantic Scholar: https://www.semanticscholar.org
• Laser AI –  https://laser.ai/
• Inciteful –  https://inciteful.xyz/
• Scite –  https://scite.ai/
• System –  https://www.system.com

If you like AI tools you may want to check out this article:

• How to get ChatGPT to write an essay [The prompts you need]

AI-powered research tools and AI for academic research

AI research tools, like Concensus, offer immense benefits in scientific research. Here are the general AI-powered tools for academic research. 

These AI-powered tools can efficiently summarize PDFs, extract key information, and perform AI-powered searches, and much more. Some are even working towards adding your own data base of files to ask questions from. 

Tools like scite even analyze citations in depth, while AI models like ChatGPT elicit new perspectives.

The result? The research process, previously a grueling endeavor, becomes significantly streamlined, offering you time for deeper exploration and understanding. Say goodbye to traditional struggles, and hello to your new AI research assistant!

• Consensus –  https://consensus.app/
• Iris AI –  https://iris.ai/
• Research Buddy –  https://researchbuddy.app/
• Mirror Think – https://mirrorthink.ai

AI for reading peer-reviewed papers easily

Using AI tools like Explain paper and Humata can significantly enhance your engagement with peer-reviewed papers. I always used to skip over the details of the papers because I had reached saturation point with the information coming in. 

These AI-powered research tools provide succinct summaries, saving you from sifting through extensive PDFs – no more boring nights trying to figure out which papers are the most important ones for you to read!

They not only facilitate efficient literature reviews by presenting key information, but also find overlooked insights.

With AI, deciphering complex citations and accelerating research has never been easier.

• Aetherbrain – https://aetherbrain.ai
• Explain Paper – https://www.explainpaper.com
• Chat PDF – https://www.chatpdf.com
• Humata – https://www.humata.ai/
• Lateral AI –  https://www.lateral.io/
• Paper Brain –  https://www.paperbrain.study/
• Scholarcy – https://www.scholarcy.com/
• SciSpace Copilot –  https://typeset.io/
• Unriddle – https://www.unriddle.ai/
• Sharly.ai – https://www.sharly.ai/
• Open Read –  https://www.openread.academy

AI for scientific writing and research papers

In the ever-evolving realm of academic research, AI tools are increasingly taking center stage.

Enter Paper Wizard, Jenny.AI, and Wisio – these groundbreaking platforms are set to revolutionize the way we approach scientific writing.

Together, these AI tools are pioneering a new era of efficient, streamlined scientific writing.

• Jenny.AI – https://jenni.ai/ (20% off with code ANDY20)
• Yomu – https://www.yomu.ai
• Wisio – https://www.wisio.app

AI academic editing tools

In the realm of scientific writing and editing, artificial intelligence (AI) tools are making a world of difference, offering precision and efficiency like never before. Consider tools such as Paper Pal, Writefull, and Trinka.

Together, these tools usher in a new era of scientific writing, where AI is your dedicated partner in the quest for impeccable composition.

• PaperPal –  https://paperpal.com/
• Writefull –  https://www.writefull.com/
• Trinka –  https://www.trinka.ai/

AI tools for grant writing

In the challenging realm of science grant writing, two innovative AI tools are making waves: Granted AI and Grantable.

These platforms are game-changers, leveraging the power of artificial intelligence to streamline and enhance the grant application process.

Granted AI, an intelligent tool, uses AI algorithms to simplify the process of finding, applying, and managing grants. Meanwhile, Grantable offers a platform that automates and organizes grant application processes, making it easier than ever to secure funding.

Together, these tools are transforming the way we approach grant writing, using the power of AI to turn a complex, often arduous task into a more manageable, efficient, and successful endeavor.

• Granted AI – https://grantedai.com/
• Grantable – https://grantable.co/

Best free AI research tools

There are many different tools online that are emerging for researchers to be able to streamline their research processes. There’s no need for convience to come at a massive cost and break the bank.

The best free ones at time of writing are:

• Elicit – https://elicit.org
• Connected Papers – https://www.connectedpapers.com/
• Litmaps – https://www.litmaps.com ( 10% off Pro subscription using the code “STAPLETON” )
• Consensus – https://consensus.app/

Wrapping up

The integration of artificial intelligence in the world of academic research is nothing short of revolutionary.

With the array of AI tools we’ve explored today – from research and mapping, literature review, peer-reviewed papers reading, scientific writing, to academic editing and grant writing – the landscape of research is significantly transformed.

The advantages that AI-powered research tools bring to the table – efficiency, precision, time saving, and a more streamlined process – cannot be overstated.

These AI research tools aren’t just about convenience; they are transforming the way we conduct and comprehend research.

They liberate researchers from the clutches of tedium and overwhelm, allowing for more space for deep exploration, innovative thinking, and in-depth comprehension.

Whether you’re an experienced academic researcher or a student just starting out, these tools provide indispensable aid in your research journey.

And with a suite of free AI tools also available, there is no reason to not explore and embrace this AI revolution in academic research.

We are on the precipice of a new era of academic research, one where AI and human ingenuity work in tandem for richer, more profound scientific exploration. The future of research is here, and it is smart, efficient, and AI-powered.

Before we get too excited however, let us remember that AI tools are meant to be our assistants, not our masters. As we engage with these advanced technologies, let’s not lose sight of the human intellect, intuition, and imagination that form the heart of all meaningful research. Happy researching!

Thank you to Ivan Aguilar – Ph.D. Student at SFU (Simon Fraser University), for starting this list for me!

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Find research papers.   Get answers.

Try Searching

How to search?

Consensus uses AI to find answers in research papers. The best way to search is to ask a question.

Ask about the relationship between concepts

Ask a simple yes/no question, ask about the effects of a concept, answers on any research topic.

Focus on questions that researchers may have studied. See example topics below ranging from biology to social sciences

Social Policy

Mental health, supplements, how you can help.

Share results on social media

Suggest topics for our blog

Report issues to support

• Research Guides
• University Libraries

AI-Based Literature Review Tools

• Dialogues: Insightful Facts
• How to Craft Prompts
• Plugins / Extensions for AI-powered Searches
• Cite ChatGPT in APA / MLA
• AI and Plagiarism
• ChatGPT & Higher Education
• Author Profile

Selected AI-Based Literature Review Tools

Updates: See news or release of AI (Beta) across various academic research databases including Web of Science , Scopus , Ebsco , ProQues t, OVID , Dimensions , JStor , Westlaw , and LexisNexis . ********* ********** ********** ********** **********   

Disclaimer: TAMU libraries do not have subscription access to the AI-powered tools listed below the divider line. The guide serves solely as an informational resource. It is recommended that you assess these tools and their usage methodologies independently. ------------------------------------------------------------------------------------------------------------------------------------------------------------- SEMANTIC SCHOLAR

• SCIENTIFIC LITERATURE SEARCH ENGINE - finding semantically similar research papers.
• " A free, AI-powered research tool for scientific literature."  <https://www.semanticscholar.org/>. But login is required in order to use all functions.
• Over 200 millions of papers from all fields of science, the data of which has also served as a wellspring for the development of other AI-driven tools.

The 4000+ results can be sorted by Fields of Study, Date Range, Author, Journals & Conferences

Save the papers in your Library folder. The Research Feeds will recommend similar papers based on the items saved.

Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality Total Citations: 22,438   [Note: these numbers were gathered when this guide was created] Highly Influential Citations 2,001 Background Citations 6,109 Methods Citations 3,273  Results Citations 385

TLDRs (Too Long; Didn't Read) Try this example . Press the pen icon to reveal the highlighted key points . TLDRs "are super-short summaries of the main objective and results of a scientific paper generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is available in beta for nearly 60 million papers in computer science, biology, and medicine..." < https://www.semanticscholar.org/product/tldr>

• AI-POWERED RESEARCH ASSISTANT - finding papers, filtering study types, automating research flow, brainstorming, summarizing and more.
• " Elicit is a research assistant using language models like GPT-3 to automate parts of researchers’ workflows. Currently, the main workflow in Elicit is Literature Review. If you ask a question, Elicit will show relevant papers and summaries of key information about those papers in an easy-to-use table."   <https://elicit.org/faq#what-is-elicit.>; Find answers from 175 million papers. FAQS
• Example - How do mental health interventions vary by age group?    /   Fish oil and depression Results: [Login required] (1) Summary of top 4 papers > Paper #1 - #4 with Title, abstract, citations, DOI, and pdf (2) Table view: Abstract / Interventions / Outcomes measured / Number of participants (3) Relevant studies and citations. (4) Click on Search for Paper Information to find - Metadata about Sources ( SJR etc.) >Population ( age etc.) >Intervention ( duration etc.) > Results ( outcome, limitations etc.) and > Methodology (detailed study design etc.) (5) Export as BIB or CSV
• How to Search / Extract Data / List of Concept Search -Enter a research question >Workflow: Searching > Summarizing 8 papers> A summary of 4 top papers > Final answers. Each result will show its citation counts, DOI, and a full-text link to Semantic Scholar website for more information such as background citations, methods citation, related papers and more. - List of Concepts search - e.g. adult learning motivation . The results will present a list the related concepts. - Extract data from a pdf file - Upload a paper and let Elicit extract data for you.
• Export Results - Various ways to export results.
• How to Cite - Includes the elicit.org URL in the citation, for example: Ought; Elicit: The AI Research Assistant; https://elicit.org; accessed xxxx/xx/xx

CONSENSUS.APP

ACADEMIC SEARCH ENGINE- using AI to find insights in research papers.

"We are a search engine that is designed to accept research questions, find relevant answers within research papers, and synthesize the results using the same language model technology." <https://consensus.app/home/blog/maximize-your-consensus-experience-with-these-best-practices/>

• Example - Does the death penalty reduce the crime?   /  Fish oil and depression  /    (1) Extracted & aggregated findings from relevant papers. (2) Results may include AIMS, DESIGN, PARTICIPANTS, FINDINGS or other methodological or report components. (3) Summaries and Full Text
• How to Search Direct questions - Does the death penalty reduce the crime? Relationship between two concepts - Fish oil and depression / Does X cause Y? Open-ended concepts - effects of immigration on local economics Tips and search examples from Consensus' Best Practice   
• Synthesize (beta) / Consensus Meter When the AI recognizes certain types of research questions, this functionality may be activated. It will examine a selection of some studies and provide a summary along with a Consensus Meter illustrating their collective agreement. Try this search: Is white rice linked to diabetes? The Consensus Meter reveals the following outcomes after analyzing 10 papers: 70% indicate a positive association, 20% suggest a possible connection, and 10% indicate no link.

Prompt “ write me a paragraph about the impact of climate change on GDP with citations “

CITATIONS IN CONTEXT

Integrated with Research Solutions.

Over 1.2 billion Citation Statements and metadata from over 181 million papers suggested reference.

How does it work? - "scite uses access to full-text articles and its deep learning model to tell you, for a given publication: - how many times it was cited by others - how it was cited by others by displaying the text where the citation happened from each citing paper - whether each citation offers supporting or contrasting evidence of the cited claims in the publication of interest, or simply mention it."   <https://help.scite.ai/en-us/article/what-is-scite-1widqmr/>

EXAMPLE of seeing all citations and citation statements in one place

More information: Scite: A smart citation index that displays the context of citations and classifies their intent using deep learning  

• GPT3.5 by OpenAI. Knowledge cutoff date is September 2021.
• Input/ Output length - ChatGPT-3.5 allows a maximum token limit of 4096 tokens. According to ChatGPT " On average, a token in English is roughly equivalent to 4 bytes or characters. English words are typically around 5 characters long. This means that, very roughly, you could fit around 800 to 1000 English words within 4096 tokens." 
• According to ChatGPT, the generated responses are non-deterministic by default. So if you run the searches again and get slightly or very different results, it's likely due to this factor.
• ChatGPT may find non-existent references.
• According to this study < https://arxiv.org/ftp/arxiv/papers/2304/2304.06794.pdf > "ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts" within the field of environmental science.  
• Example - "INTERVIEW WITH CHATGPT" as a Research Method & Teaching Tool Some researchers began to use this approach to obtain their research data. Try this Google Scholar search link "interview with ChatGPT"   or see two articles below: (1) Chatting about ChatGPT: how may AI and GPT impact academia and libraries? BD Lund, T Wang - Library Hi Tech News, 2023 (2) An interview with ChatGPT: discussing artificial intelligence in teaching, research, and practice , G Scaringi, M Loche - 2023  

Increased risk of sudden infant death syndrome (SIDS) Increased risk of premature birth Increased risk of low birth weight Increased risk of respiratory problems in newborns Increased risk of respiratory problems in infants exposed to secondhand smoke Increased risk of developing asthma and other respiratory illnesses later in life for infants exposed to secondhand smoke [Note : ChatGPT may generate non-existent references or false knowledge. To find out why Large Language Models hallucinate, check out this Wiki article: Hallucination (artificial intelligence) and this blog post -   A Gentle Introduction to Hallucinations in Large Language Models by Adrian Tam ]

Infant death Neonatal mortality (referring specifically to deaths within the first 28 days of life) Perinatal mortality (referring to deaths occurring during the period from 22 completed weeks of gestation to 7 completed days after birth) Early childhood mortality (referring to deaths occurring within the first five years of life) Child mortality (referring to deaths occurring before the age of 18) [Press the Regenerate button to get more.]

• Example -  RELATED WORDS What are the related words of infant mortality? Neonatal mortality, Post-neonatal mortality, Stillbirths, Low birth weight, Malnutrition, Infectious diseases, Vaccination, Maternal health,  Access to healthcare, Poverty, Social inequality, Sanitation, Hygiene, Water quality, Childbirth complications, Congenital abnormalities, Birth defects, Maternal age, Under-five mortality, Child mortality, Perinatal mortality, Preterm birth, Low birth weight, Sudden infant death syndrome (SIDS), Maternal mortality, Postnatal care, Malnutrition, Immunization, Access to healthcare, Clean water and sanitation, Congenital anomalies, Infant health disparities, Infant mortality rate (IMR), Infant survival.  

(("Infant Death"[Mesh] OR "Sudden Infant Death Syndrome"[Mesh] OR "Infant Mortality"[Mesh] OR "Perinatal Mortality"[Mesh] OR "Neonatal Mortality"[Mesh] OR "Fetal Mortality"[Mesh] OR "Infant Death" OR "Sudden Infant Death Syndrome" OR "Infant Mortality" OR "Perinatal Mortality" OR "Neonatal Mortality" OR "Fetal Mortality") AND ("Risk Factors"[Mesh] OR "Etiology"[Mesh] OR "Prevention and Control"[Mesh] OR "Interventions"[Mesh] OR "Public Health"[Mesh] OR "Health Disparities"[Mesh] OR "Healthcare Disparities"[Mesh] OR "Poverty"[Mesh] OR "Malnutrition"[Mesh] OR "Infection"[Mesh] OR "Congenital Abnormalities"[Mesh] OR "Prematurity"[Mesh] OR "Low Birth Weight"[Mesh] OR "Maternal Education"[Mesh] OR "Maternal Health"[Mesh] OR "Risk Factors" OR "Etiology" OR "Prevention and Control" OR "Interventions" OR "Public Health" OR "Health Disparities" OR "Healthcare Disparities" OR "Poverty" OR "Malnutrition" OR "Infection" OR "Congenital Abnormalities" OR "Prematurity" OR "Low Birth Weight" OR "Maternal Education" OR "Maternal Health")) Comments and Suggestions: #1 -This search string may not work on all database platforms. For example, Medline (OVID) may not be able to run it, Medline & CINAHL (EBSCO) can run it without any problems while PubMed will run it but it will indicate which MeSH terms are not indexed. See PubMed's search History and Details under Advanced . #2 - This is just one possible combination. You may need to adjust it based on your task and the databases you are using . #3 - It might be easier if you break the task into 3 parts: ask for synonyms > ask for thesauri terms > and ask it to combine them.

Examples - DATABASE RECOMMENDATIONS Heath Science - Which databases to use to find articles on the EFFECTS OF MATERNAL SMOKING ON INFANT DEATH? PubMed: This is a database of biomedical literature from the National Library of Medicine. It includes articles from medical journals and other sources on a wide range of health-related topics. Embase: This is a database of biomedical literature that covers more international and pharmaceutical content than PubMed. It includes articles from medical journals and other sources on a wide range of health-related topics. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions, including interventions related to maternal smoking and infant death. Scopus: This is a multidisciplinary database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. Web of Science: This is a database that covers research from a wide range of fields, including health sciences. It includes articles from scientific journals, books, and conference proceedings. CINAHL: This is a database of nursing and allied health literature, including articles on maternal smoking and infant death. [Note: The response above was copied and pasted directly from ChatGPT. No editing was added.] Education -- I am doing a meta-analysis on k-12 STEM education. What databases should I use? ERIC : This is a database of education research and information, including articles from journals, reports, and conference papers. It is a commonly used database for educational research. Education Source : This is a comprehensive database of education research and information, including articles from journals, books, and conference papers. Web of Science: This is a multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. Scopus: This is another multidisciplinary database that covers research from a wide range of fields, including education. It includes articles from scientific journals, books, and conference proceedings. PsycINFO: This is a database of psychology research, including articles from journals, books, and dissertations. It can be useful for research on STEM education that includes psychological factors. Cochrane Library : This is a collection of databases that provides systematic reviews and meta-analyses of healthcare interventions including interventions related to education. [Author's note: You could also ask for the GREY LITERATURE sources related to the topic above,]

Example: ACT-AS-AN-EXPERT PROMPT Here's an alternative way to consolidate all the questions into a single consultation by using this popular Act-As-An-Expert prompt, aka, system message prompt:  I am going to conduct a systematic review on games and mathematics related to K-12 education  I want you to act as a systematic review expert . I will ask you some questions related to my research topic and you advise me on how to do it. 

[You may ask one question at a time] My first question is "which databases should I use?"  My second question is "what are the relevant subject terms, descriptors and key words?" My third question is "how to do data extraction?" ..... , .... Please note that the above prompts are merely for illustrative purposes. Actual questions may contain more specific instructions. As an example, for the first question, could you provide guidance on how to identify relevant publications? Specifically, can you provide a list of the primary databases and grey literature sources related to my topic?  

Example - GREY LITERATURE Please show me all the resources that offer grey literature for conducting research in the field of education     ERIC (Education Resources Information Center): https://eric.ed.gov/     OpenGrey: http://www.opengrey.eu/     British Education Index: https://www.ebscohost.com/academic/british-education-index     WorldCat: https://www.worldcat.org/     ProQuest Dissertations & Theses Global: https://www.proquest.com/products-services/pqdtglobal.html     EThOS (Electronic Theses Online Service): https://ethos.bl.uk/     Institutional Repositories of universities and academic institutions (search for specific institution repositories)     American Educational Research Association (AERA): https://www.aera.net/     National Education Association (NEA): https://www.nea.org/     Association for Supervision and Curriculum Development (ASCD): http://www.ascd.org/     RAND Corporation: https://www.rand.org/     National Center for Education Research (NCER): https://ies.ed.gov/ncer/     National Center for Education Statistics (NCES): https://nces.ed.gov/     European Educational Research Association (EERA): https://www.eera-ecer.de/     UNESCO International Institute for Educational Planning (IIEP): http://www.iiep.unesco.org/     Organization for Economic Cooperation and Development (OECD): https://www.oecd.org/education/     Education Development Center (EDC): https://www.edc.org/     National Institute for Educational Policy Research (NIER) - Japan: https://www.nier.go.jp/     Australian Council for Educational Research (ACER): https://www.acer.org/     Canadian Education Association (CEA): https://www.cea-ace.ca/ My topic is about stem education. Which grey literature databases should I use?    STEM Education Research Centre (SERC) Grey Literature Database    National STEM Education Research Repository (NSERR)    National Science Digital Library (NSDL)    STEM Education Resource Center (SERC) GrayLit Network    STEM Education Grey Literature Library

See other Comparison Examples under Bing AI.

Examples - ZERO SHOT, ONE SHOT & FEW SHOT PROMPTING for literature review See the examples on the left panel- How to Fine Tune Prompts

Bing Chat / Copilot

• Bing Chat has become Copilot.
• CONVERSATIONAL LLM 4.0 + SEARCH ENGINE. Connects to the Internet.
• Three conversation modes: More Creative, More Balanced or More Precise.
• Comparison - Prompt: My topic is about psychology. Which grey literature databases should I use? More Precise - PsycExtra, NIH Library and links to library guides, .gov and .org websites More Balanced - PsycExtra and three main research guides that mention psychology grey literature sources. More Creative- PsycExtra, LILACS, and Worldcat + definition of grey literature + suggestions on searching for professional association websites, newsletters, magazines, standards and guidelines, and other sources that may contain relevant information for your topic.
• Some examples below were tested in Bing Chat only.  
• Example - factors of infant mortality Infant mortality is a term that refers to the death of infants before their first birthday. The leading causes of infant mortality include birth asphyxia, pneumonia, congenital malformations, term birth complications such as abnormal presentation of the fetus umbilical cord prolapse, or prolonged labor, neonatal infection, diarrhea, malaria, measles, and malnutrition1. Many situational factors lead to infant mortality such as the pregnant woman’s level of education, environmental conditions, political infrastructure, and level of medical support1. In the United States, a primary determinant of infant mortality risk is infant birth weight with lower birth weights increasing the risk of infant mortality. The determinants of low birth weight include socioeconomic, psychological, behavioral and environmental factors2.  
• Example: PEER REVIEWED SOURCES I need to find some peer reviewed articles about infant mortality? The answer includes 5 articles. The first one is “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” by Neha Bairoliya and Günther Fink1. A click on  " Tell me more about the first article " leads to this summary: " The first article is titled “Causes of death and infant mortality rates among full-term births in the United States between 2010 and 2012: An observational study” and was published in PLOS Medicine on March 20, 2018. The authors are Neha Bairoliya and Günther Fink. The study used linked birth and death records for the period 2010–2012 to identify the state- and cause-specific burden of infant mortality among full-term infants (born at 37–42 weeks of gestation) in the United States. The researchers found that the full-term infant mortality rate (FTIMR) was 2.2 per 1,000 live births overall and ranged between 1.29 (Connecticut) and 3.77 (Mississippi) at the state level. Sudden unexpected death in infancy (SUDI) accounted for 43% of FTIM; congenital malformations and perinatal conditions accounted for 31% and 11.3% of FTIM, respectively. The largest mortality differentials between states with good and states with poor FTIMR were found for SUDI, with particularly large risk differentials for deaths due to sudden infant death syndrome (SIDS) and suffocation." More searches: Please find five empirical studies focusing on the factors influencing adult learners engaged in online education. Please locate five scholarly articles on stress management among college students site:pubmed.ncbi.nlm.nih.gov

The ERIC Thesaurus contains nearly 12,000 terms, including more than 4,500 descriptors and 7,000 synonyms1. You can use the term “Academic Achievement” or its synonyms such as “Educational Achievement”, “Student Achievement”, “Academic Performance”, “Academic Success”, “Learning Achievement” and more. [ Note : The follow-up responses include some additional sources. See two below: https://www.powerthesaurus.org/academic_achievement https://eric.ed.gov/?ti=Achievement+Gap   including https://eric.ed.gov/?ti=Academic+Achievement |

My topic is about psychology.  Which grey literature databases should I use?

ChatGPT PsycEXTRA : This database is produced by the American Psychological Association (APA) and includes grey literature such as conference papers, white papers, and government reports. OpenGrey : This database provides access to grey literature produced in Europe, including reports, theses, and conference papers Grey Literature Report : This database is produced by The New York Academy of Medicine and includes reports, conference papers, and other grey literature on health and biomedical topics, including psychology. ProQuest Dissertations and Theses Global : This database provides access to graduate-level research, including theses and dissertations related to psychology. Google Scholar: While not exclusively a grey literature database, Google Scholar can be a useful tool for finding conference papers and other grey literature related to psychology. National Technical Information Service (NTIS) : This database provides access to technical reports produced by U.S. government agencies, including those related to psychology. Bing AI   - [asked in the Precise mode] For psychology, some recommended grey literature databases include PsycEXTRA and PsyArXiv . PsycEXTRA is a database of grey literature material relating to psychology, behavioral sciences and health. PsyArXiv is a psychology archive designed to facilitate rapid dissemination of psychological research. What other models have been developed based on SERVQUAL?

ChatGPT SERVPERF: This is a modified version of SERVQUAL that measures service performance instead of service quality. It was developed by Cronin and Taylor (1992) and is based on the same five dimensions as SERVQUAL. SERVPERF-GAP: This model, developed by Caruana and Ewing (2006), extends the SERVQUAL model to include three additional gaps that can occur when customers evaluate service quality. E-SERVQUAL: This model, developed by Parasuraman et al. (2005), adapts the SERVQUAL scale to measure the quality of online services. SERVCO: This is a modified version of SERVQUAL that includes a sixth dimension, "cost," in addition to the five original dimensions. It was developed by Sureshchandar et al. (2002) to address the importance of cost in service quality evaluation. SERVQ-HC: This is a modified version of SERVQUAL that is specifically designed for evaluating the quality of health care services. It was developed by Cronin et al. (2000) and includes 20 items across five dimensions. Bing AI The Nordic model of service quality2. The hierarchical model of service quality3. The American Customer Satisfaction Index (ACSI)4.

     Bing AI Sidebar - CHAT, THINK, & WRITE

• Examples of Using AI sidebar to Recap Google Scholar findings

Chat - If you highlight a study in the search results of Google Scholar, you will be prompted with a question by AI sidebar asking if you want to send the selected text to it. If you choose to do so, you can then select either  EXPLAIN or EXPAND to learn more about the chosen article. It's worth noting that EXPAND provides more detailed information. You can then click on any of the follow-up links to delve further into the selected article or topic. If the text of the chosen study is written in a foreign language, the AI sidebar can also provide an explanation of the text in English. Another option for extracting the key points from a selected article is to submit the URL of the PDF. Insights - Use the insights button to get more ideas about the topic. Compose - Tell the Edge sidebar your topic and let its Compose tool to generate a draft for you. Google Scholar Button- See also the Plugins and Extension page for how to perform a combined search using Google, Google Scholar, and ChatGPT .

Example: FINDING SIMILAR ARTICLES Find similar articles like this one - [then paste in the abstract ] Note - Use this prompt with Bing chat since real-time web info is required.

Examples: SUMMARIZE + REFERENCE Use a basic prompt like " Please summarize . ..." or add a REFERENCE TEXT that provides the necessary information about what you want it to focus or how the summary or resolution should look like. The reference could be a quote, an excerpt, a partial sentence, a conversation, an abstract, a code snippet and so on. Formula : Specify a role > assign a task > provide a reference text. Example#1 - Scholarly Journal Quote

STEP 1 Prompt: As a research assistant specializing in renewable energy, your task is to locate comparable research studies based on the provided abstract from an article: "This paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and replacement of fossil fuels by various sources of renewable energy."

Bing Chat then found 3 documents: the ScienceDirect paper where the abstract came from and two other documents from un.org and frontiersin.org respectively.

STEP 2 Prompt: Please synthesize the findings of the three studies provided above.

Bing Chat: "Sure! Here is a synthesis of the findings from the three studies:

All three studies emphasize the importance of renewable energy in achieving sustainable development and mitigating climate change. They all discuss various strategies and actions that can be taken to increase the use of renewable energy sources and reduce reliance on fossil fuels.

Henrik Lund’s paper discusses the perspective of renewable energy (wind, solar, wave and biomass) in the making of strategies for a sustainable development. Such strategies typically involve three major technological changes: energy savings on the demand side, efficiency improvements in the energy production, and .....

The United Nations outlines five critical actions the world needs to prioritize now to transform our energy systems and speed up the shift to renewable energy: Make renewable energy technology a global public good, Improve global access to components and raw materials......

“Sustainable Energy Transition for Renewable and Low Carbon Grid” discusses that a sustainable global electricity transition will entail increased use of renewable energy sources particularly wind and solar, nuclear energy as a low carbon energy source, electrification of transport and.......

In summary , these studies suggest that transitioning to renewable energy sources is crucial for sustainable development and mitigating climate change. This can be achieved through various strategies such as increasing energy efficiency, improving access to renewable technology and materials, leveling the playing field for renewables, ending fossil fuel subsidies, and redirecting investments towards renewables." Example #2 Y ou are an expert researcher, given the following article, please discuss its key findings. Reference: How Large Language Models are Transforming Machine-Paraphrased Plagiarism at https://arxiv.org/abs/2210.03568 This is another way to put REFERENCE TEXT. As a side not, role specifying or the use of persona is important as it can impact the level of responses obtained. Just imagine if the designated role were " You are a high school student... ." Example #3 Please read this article and summarize it f or me - "Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making" and then find 5 similar studies and please also summarize each for me.

CONNECTED PAPERS

• RELATED STUDIES
• Uses visual graphs or other ways to show relevant studies. The database is connected to the Semantic Scholar Paper Corpus which has compiled hundreds of millions of published papers across many science and social science fields.
• See more details about how it works .  
• Example - SERVQUAL and then click on SELECT A PAPER TO BUILD THE GRAPH > The first paper was selected. Results: (1) Origin paper - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality + Connected papers with links to Connected Papers / PDF / DOI or Publisher's site / Semantic Scholar / Google Scholar. (2) Graph showing the origin paper + connected papers with links to the major sources . See above. (3) Links to Prior Works and Derivative Works See the detailed citations by Semantic Scholar on the origin SERVQUAL paper on the top of this page within Semantic Scholars.
• How to Search Search by work title. Enter some keywords about a topic.
• Download / Save Download your saved Items in Bib format.

PAPER DIGEST

• SUMMARY & SYNTHESIS
• " Knowledge graph & natural language processing platform tailored for technology domain . <"https://www.paperdigest.org/> Areas covered: technology, biology/health, all sciences areas, business, humanities/ social sciences, patents and grants ...

• LITERATURE REVIEW - https://www.paperdigest.org/review/ Systematic Review - https://www.paperdigest.org/literature-review/
• SEARCH CONSOLE - https://www.paperdigest.org/search/ Conference Digest - NIPS conference papers ... Tech AI Tools: Literature Review  | Literature Search | Question Answering | Text Summarization Expert AI Tools: Org AI | Expert search | Executive Search, Reviewer Search, Patent Lawyer Search...

Daily paper digest / Conference papers digest / Best paper digest / Topic tracking. In Account enter the subject areas interested. Daily Digest will upload studies based on your interests.

RESEARCH RABBIT

• CITATION-BASED MAPPING: SIMILAR / EARLY / LATER WORKS
• " 100s of millions of academic articles and covers more than 90%+ of materials that can be found in major databases used by academic institutions (such as Scopus, Web of Science, and others) ." See its FAQs page. Search algorithms were borrowed from NIH and Semantic Scholar.

The default “Untitled Collection” will collect your search histories, based on which Research Rabbit will send you recommendations for three types of related results: Similar Works / Earlier Works / Later Works, viewable in graph such as Network, Timeline, First Authors etc.

Zotero integration: importing and exporting between these two apps.

• Example - SERVQUAL: A multiple-item scale for measuring consumer perceptions of service quality [Login required] Try it to see its Similar Works, Earlier Works and Later Works or other documents.
• Export Results - Findings can be exported in BibTxt, RIS or CSV format.

CITING GENERATIVE AI

• How to cite ChatGPT  [APA] - https://apastyle. apa.org/blog /how-to-cite-chatgpt  
• How to Cite Generative AI  [MLA]  https://style. mla.org /citing-generative-ai/
• Citation Guide - Citing ChatGPT and Other Generative AI (University of Queensland, Australia)
• Next: Dialogues: Insightful Facts >>
• Last Updated: May 6, 2024 10:40 AM
• URL: https://tamu.libguides.com/c.php?g=1289555

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Published: 02 August 2023

Scientific discovery in the age of artificial intelligence

• Hanchen Wang   ORCID: orcid.org/0000-0002-1691-024X 1 , 2   na1   nAff37   nAff38 ,
• Tianfan Fu 3   na1 ,
• Yuanqi Du 4   na1 ,
• Wenhao Gao 5 ,
• Kexin Huang 6 ,
• Ziming Liu 7 ,
• Payal Chandak   ORCID: orcid.org/0000-0003-1097-803X 8 ,
• Shengchao Liu   ORCID: orcid.org/0000-0003-2030-2367 9 , 10 ,
• Peter Van Katwyk   ORCID: orcid.org/0000-0002-3512-0665 11 , 12 ,
• Andreea Deac 9 , 10 ,
• Anima Anandkumar 2 , 13 ,
• Karianne Bergen 11 , 12 ,
• Carla P. Gomes   ORCID: orcid.org/0000-0002-4441-7225 4 ,
• Shirley Ho 14 , 15 , 16 , 17 ,
• Pushmeet Kohli   ORCID: orcid.org/0000-0002-7466-7997 18 ,
• Joan Lasenby 1 ,
• Jure Leskovec   ORCID: orcid.org/0000-0002-5411-923X 6 ,
• Tie-Yan Liu 19 ,
• Arjun Manrai 20 ,
• Debora Marks   ORCID: orcid.org/0000-0001-9388-2281 21 , 22 ,
• Bharath Ramsundar 23 ,
• Le Song 24 , 25 ,
• Jimeng Sun 26 ,
• Jian Tang 9 , 27 , 28 ,
• Petar Veličković 18 , 29 ,
• Max Welling 30 , 31 ,
• Linfeng Zhang 32 , 33 ,
• Connor W. Coley   ORCID: orcid.org/0000-0002-8271-8723 5 , 34 ,
• Yoshua Bengio   ORCID: orcid.org/0000-0002-9322-3515 9 , 10 &
• Marinka Zitnik   ORCID: orcid.org/0000-0001-8530-7228 20 , 22 , 35 , 36  

Nature volume  620 ,  pages 47–60 ( 2023 ) Cite this article

96k Accesses

143 Citations

598 Altmetric

Metrics details

• Computer science
• Machine learning
• Scientific community

A Publisher Correction to this article was published on 30 August 2023

This article has been updated

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate hypotheses, design experiments, collect and interpret large datasets, and gain insights that might not have been possible using traditional scientific methods alone. Here we examine breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the structure of scientific data to enhance model accuracy and efficiency. Generative AI methods can create designs, such as small-molecule drugs and proteins, by analysing diverse data modalities, including images and sequences. We discuss how these methods can help scientists throughout the scientific process and the central issues that remain despite such advances. Both developers and users of AI tools need a better understanding of when such approaches need improvement, and challenges posed by poor data quality and stewardship remain. These issues cut across scientific disciplines and require developing foundational algorithmic approaches that can contribute to scientific understanding or acquire it autonomously, making them critical areas of focus for AI innovation.

This is a preview of subscription content, access via your institution

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Buy this article

• Purchase on Springer Link
• Instant access to full article PDF

Prices may be subject to local taxes which are calculated during checkout

Similar content being viewed by others

Accelerating science with human-aware artificial intelligence

Accelerating material design with the generative toolkit for scientific discovery

Why big data and compute are not necessarily the path to big materials science

Change history, 30 august 2023.

A Correction to this paper has been published: https://doi.org/10.1038/s41586-023-06559-7

LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521 , 436–444 (2015). This survey summarizes key elements of deep learning and its development in speech recognition, computer vision and and natural language processing .

Article   ADS   CAS   PubMed   Google Scholar  

de Regt, H. W. Understanding, values, and the aims of science. Phil. Sci. 87 , 921–932 (2020).

Article   MathSciNet   Google Scholar  

Pickstone, J. V. Ways of Knowing: A New History of Science, Technology, and Medicine (Univ. Chicago Press, 2001).

Han, J. et al. Deep potential: a general representation of a many-body potential energy surface. Commun. Comput. Phys. 23 , 629–639 (2018). This paper introduced a deep neural network architecture that learns the potential energy surface of many-body systems while respecting the underlying symmetries of the system by incorporating group theory.

Akiyama, K. et al. First M87 Event Horizon Telescope results. IV. Imaging the central supermassive black hole. Astrophys. J. Lett. 875 , L4 (2019).

Article   ADS   CAS   Google Scholar  

Wagner, A. Z. Constructions in combinatorics via neural networks. Preprint at https://arxiv.org/abs/2104.14516 (2021).

Coley, C. W. et al. A robotic platform for flow synthesis of organic compounds informed by AI planning. Science 365 , eaax1566 (2019).

Article   CAS   PubMed   Google Scholar  

Bommasani, R. et al. On the opportunities and risks of foundation models. Preprint at https://arxiv.org/abs/2108.07258 (2021).

Davies, A. et al. Advancing mathematics by guiding human intuition with AI. Nature 600 , 70–74 (2021). This paper explores how AI can aid the development of pure mathematics by guiding mathematical intuition.

Article   ADS   CAS   PubMed   PubMed Central   MATH   Google Scholar  

Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596 , 583–589 (2021). This study was the first to demonstrate the ability to predict protein folding structures using AI methods with a high degree of accuracy, achieving results that are at or near the experimental resolution. This accomplishment is particularly noteworthy, as predicting protein folding has been a grand challenge in the field of molecular biology for over 50 years.

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Stokes, J. M. et al. A deep learning approach to antibiotic discovery. Cell 180 , 688–702 (2020).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Bohacek, R. S., McMartin, C. & Guida, W. C. The art and practice of structure-based drug design: a molecular modeling perspective. Med. Res. Rev. 16 , 3–50 (1996).

Bileschi, M. L. et al. Using deep learning to annotate the protein universe. Nat. Biotechnol. 40 , 932–937 (2022).

Bellemare, M. G. et al. Autonomous navigation of stratospheric balloons using reinforcement learning. Nature 588 , 77–82 (2020). This paper describes a reinforcement-learning algorithm for navigating a super-pressure balloon in the stratosphere, making real-time decisions in the changing environment.

Tshitoyan, V. et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature 571 , 95–98 (2019).

Zhang, L. et al. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics. Phys. Rev. Lett. 120 , 143001 (2018).

Deiana, A. M. et al. Applications and techniques for fast machine learning in science. Front. Big Data 5 , 787421 (2022).

Karagiorgi, G. et al. Machine learning in the search for new fundamental physics. Nat. Rev. Phys. 4 , 399–412 (2022).

Zhou, C. & Paffenroth, R. C. Anomaly detection with robust deep autoencoders. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 665–674 (2017).

Hinton, G. E. & Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science 313 , 504–507 (2006).

Article   ADS   MathSciNet   CAS   PubMed   MATH   Google Scholar  

Kasieczka, G. et al. The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics. Rep. Prog. Phys. 84 , 124201 (2021).

Govorkova, E. et al. Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider. Nat. Mach. Intell. 4 , 154–161 (2022).

Article   Google Scholar  

Chamberland, M. et al. Detecting microstructural deviations in individuals with deep diffusion MRI tractometry. Nat. Comput. Sci. 1 , 598–606 (2021).

Article   PubMed   PubMed Central   Google Scholar  

Rafique, M. et al. Delegated regressor, a robust approach for automated anomaly detection in the soil radon time series data. Sci. Rep. 10 , 3004 (2020).

Pastore, V. P. et al. Annotation-free learning of plankton for classification and anomaly detection. Sci. Rep. 10 , 12142 (2020).

Naul, B. et al. A recurrent neural network for classification of unevenly sampled variable stars. Nat. Astron. 2 , 151–155 (2018).

Article   ADS   Google Scholar  

Lee, D.-H. et al. Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In ICML Workshop on Challenges in Representation Learning (2013).

Zhou, D. et al. Learning with local and global consistency. In Advances in Neural Information Processing Systems 16 , 321–328 (2003).

Radivojac, P. et al. A large-scale evaluation of computational protein function prediction. Nat. Methods 10 , 221–227 (2013).

Barkas, N. et al. Joint analysis of heterogeneous single-cell RNA-seq dataset collections. Nat. Methods 16 , 695–698 (2019).

Tran, K. & Ulissi, Z. W. Active learning across intermetallics to guide discovery of electrocatalysts for CO 2 reduction and H 2 evolution. Nat. Catal. 1 , 696–703 (2018).

Article   CAS   Google Scholar  

Jablonka, K. M. et al. Bias free multiobjective active learning for materials design and discovery. Nat. Commun. 12 , 2312 (2021).

Roussel, R. et al. Turn-key constrained parameter space exploration for particle accelerators using Bayesian active learning. Nat. Commun. 12 , 5612 (2021).

Ratner, A. J. et al. Data programming: creating large training sets, quickly. In Advances in Neural Information Processing Systems 29 , 3567–3575 (2016).

Ratner, A. et al. Snorkel: rapid training data creation with weak supervision. In International Conference on Very Large Data Bases 11 , 269–282 (2017). This paper presents a weakly-supervised AI system designed to annotate massive amounts of data using labeling functions.

Butter, A. et al. GANplifying event samples. SciPost Phys. 10 , 139 (2021).

Brown, T. et al. Language models are few-shot learners. In Advances in Neural Information Processing Systems 33 , 1877–1901 (2020).

Ramesh, A. et al. Zero-shot text-to-image generation. In International Conference on Machine Learning 139 , 8821–8831 (2021).

Littman, M. L. Reinforcement learning improves behaviour from evaluative feedback. Nature 521 , 445–451 (2015).

Cubuk, E. D. et al. Autoaugment: learning augmentation strategies from data. In IEEE Conference on Computer Vision and Pattern Recognition 113–123 (2019).

Reed, C. J. et al. Selfaugment: automatic augmentation policies for self-supervised learning. In IEEE Conference on Computer Vision and Pattern Recognition 2674–2683 (2021).

ATLAS Collaboration et al. Deep generative models for fast photon shower simulation in ATLAS. Preprint at https://arxiv.org/abs/2210.06204 (2022).

Mahmood, F. et al. Deep adversarial training for multi-organ nuclei segmentation in histopathology images. IEEE Trans. Med. Imaging 39 , 3257–3267 (2019).

Teixeira, B. et al. Generating synthetic X-ray images of a person from the surface geometry. In IEEE Conference on Computer Vision and Pattern Recognition 9059–9067 (2018).

Lee, D., Moon, W.-J. & Ye, J. C. Assessing the importance of magnetic resonance contrasts using collaborative generative adversarial networks. Nat. Mach. Intell. 2 , 34–42 (2020).

Kench, S. & Cooper, S. J. Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion. Nat. Mach. Intell. 3 , 299–305 (2021).

Wan, C. & Jones, D. T. Protein function prediction is improved by creating synthetic feature samples with generative adversarial networks. Nat. Mach. Intell. 2 , 540–550 (2020).

Repecka, D. et al. Expanding functional protein sequence spaces using generative adversarial networks. Nat. Mach. Intell. 3 , 324–333 (2021).

Marouf, M. et al. Realistic in silico generation and augmentation of single-cell RNA-seq data using generative adversarial networks. Nat. Commun. 11 , 166 (2020).

Ghahramani, Z. Probabilistic machine learning and artificial intelligence. Nature 521 , 452–459 (2015). This survey provides an introduction to probabilistic machine learning, which involves the representation and manipulation of uncertainty in models and predictions, playing a central role in scientific data analysis.

Cogan, J. et al. Jet-images: computer vision inspired techniques for jet tagging. J. High Energy Phys. 2015 , 118 (2015).

Zhao, W. et al. Sparse deconvolution improves the resolution of live-cell super-resolution fluorescence microscopy. Nat. Biotechnol. 40 , 606–617 (2022).

Brbić, M. et al. MARS: discovering novel cell types across heterogeneous single-cell experiments. Nat. Methods 17 , 1200–1206 (2020).

Article   PubMed   Google Scholar  

Qiao, C. et al. Evaluation and development of deep neural networks for image super-resolution in optical microscopy. Nat. Methods 18 , 194–202 (2021).

Andreassen, A. et al. OmniFold: a method to simultaneously unfold all observables. Phys. Rev. Lett. 124 , 182001 (2020).

Bergenstråhle, L. et al. Super-resolved spatial transcriptomics by deep data fusion. Nat. Biotechnol. 40 , 476–479 (2021).

Vincent, P. et al. Extracting and composing robust features with denoising autoencoders. In International Conference on Machine Learning 1096–1103 (2008).

Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. In International Conference on Learning Representations (2014).

Eraslan, G. et al. Single-cell RNA-seq denoising using a deep count autoencoder. Nat. Commun. 10 , 390 (2019).

Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016).

Olshausen, B. A. & Field, D. J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381 , 607–609 (1996).

Bengio, Y. Deep learning of representations for unsupervised and transfer learning. In ICML Workshop on Unsupervised and Transfer Learning (2012).

Detlefsen, N. S., Hauberg, S. & Boomsma, W. Learning meaningful representations of protein sequences. Nat. Commun. 13 , 1914 (2022).

Becht, E. et al. Dimensionality reduction for visualizing single-cell data using UMAP. Nat. Biotechnol. 37 , 38–44 (2019).

Bronstein, M. M. et al. Geometric deep learning: going beyond euclidean data. IEEE Signal Process Mag. 34 , 18–42 (2017).

Anderson, P. W. More is different: broken symmetry and the nature of the hierarchical structure of science. Science 177 , 393–396 (1972).

Qiao, Z. et al. Informing geometric deep learning with electronic interactions to accelerate quantum chemistry. Proc. Natl Acad. Sci. USA 119 , e2205221119 (2022).

Bogatskiy, A. et al. Symmetry group equivariant architectures for physics. Preprint at https://arxiv.org/abs/2203.06153 (2022).

Bronstein, M. M. et al. Geometric deep learning: grids, groups, graphs, geodesics, and gauges. Preprint at https://arxiv.org/abs/2104.13478 (2021).

Townshend, R. J. L. et al. Geometric deep learning of RNA structure. Science 373 , 1047–1051 (2021).

Wicky, B. I. M. et al. Hallucinating symmetric protein assemblies. Science 378 , 56–61 (2022).

Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (2017).

Veličković, P. et al. Graph attention networks. In International Conference on Learning Representations (2018).

Hamilton, W. L., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems 30 , 1024–1034 (2017).

Gilmer, J. et al. Neural message passing for quantum chemistry. In International Conference on Machine Learning 1263–1272 (2017).

Li, M. M., Huang, K. & Zitnik, M. Graph representation learning in biomedicine and healthcare. Nat. Biomed. Eng. 6 , 1353–1369 (2022).

Satorras, V. G., Hoogeboom, E. & Welling, M. E( n ) equivariant graph neural networks. In International Conference on Machine Learning 9323–9332 (2021). This study incorporates principles of physics into the design of neural models, advancing the field of equivariant machine learning .

Thomas, N. et al. Tensor field networks: rotation-and translation-equivariant neural networks for 3D point clouds. Preprint at https://arxiv.org/abs/1802.08219 (2018).

Finzi, M. et al. Generalizing convolutional neural networks for equivariance to lie groups on arbitrary continuous data. In International Conference on Machine Learning 3165–3176 (2020).

Fuchs, F. et al. SE(3)-transformers: 3D roto-translation equivariant attention networks. In Advances in Neural Information Processing Systems 33 , 1970-1981 (2020).

Zaheer, M. et al. Deep sets. In Advances in Neural Information Processing Systems 30 , 3391–3401 (2017). This paper is an early study that explores the use of deep neural architectures on set data, which consists of an unordered list of elements.

Cohen, T. S. et al. Spherical CNNs. In International Conference on Learning Representations (2018).

Gordon, J. et al. Permutation equivariant models for compositional generalization in language. In International Conference on Learning Representations (2019).

Finzi, M., Welling, M. & Wilson, A. G. A practical method for constructing equivariant multilayer perceptrons for arbitrary matrix groups. In International Conference on Machine Learning 3318–3328 (2021).

Dijk, D. V. et al. Recovering gene interactions from single-cell data using data diffusion. Cell 174 , 716–729 (2018).

Gainza, P. et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat. Methods 17 , 184–192 (2020).

Hatfield, P. W. et al. The data-driven future of high-energy-density physics. Nature 593 , 351–361 (2021).

Bapst, V. et al. Unveiling the predictive power of static structure in glassy systems. Nat. Phys. 16 , 448–454 (2020).

Zhang, R., Zhou, T. & Ma, J. Multiscale and integrative single-cell Hi-C analysis with Higashi. Nat. Biotechnol. 40 , 254–261 (2022).

Sammut, S.-J. et al. Multi-omic machine learning predictor of breast cancer therapy response. Nature 601 , 623–629 (2022).

DeZoort, G. et al. Graph neural networks at the Large Hadron Collider. Nat. Rev. Phys . 5 , 281–303 (2023).

Liu, S. et al. Pre-training molecular graph representation with 3D geometry. In International Conference on Learning Representations (2022).

The LIGO Scientific Collaboration. et al. A gravitational-wave standard siren measurement of the Hubble constant. Nature 551 , 85–88 (2017).

Reichstein, M. et al. Deep learning and process understanding for data-driven Earth system science. Nature 566 , 195–204 (2019).

Goenka, S. D. et al. Accelerated identification of disease-causing variants with ultra-rapid nanopore genome sequencing. Nat. Biotechnol. 40 , 1035–1041 (2022).

Bengio, Y. et al. Greedy layer-wise training of deep networks. In Advances in Neural Information Processing Systems 19 , 153–160 (2006).

Hinton, G. E., Osindero, S. & Teh, Y.-W. A fast learning algorithm for deep belief nets. Neural Comput. 18 , 1527–1554 (2006).

Article   MathSciNet   PubMed   MATH   Google Scholar  

Jordan, M. I. & Mitchell, T. M. Machine learning: trends, perspectives, and prospects. Science 349 , 255–260 (2015).

Devlin, J. et al. BERT: pre-training of deep bidirectional transformers for language understanding. In North American Chapter of the Association for Computational Linguistics 4171–4186 (2019).

Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl Acad. Sci. USA 118 , e2016239118 (2021).

Elnaggar, A. et al. ProtTrans: rowards cracking the language of lifes code through self-supervised deep learning and high performance computing. In IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).

Hie, B. et al. Learning the language of viral evolution and escape. Science 371 , 284–288 (2021). This paper modeled viral escape with machine learning algorithms originally developed for human natural language.

Biswas, S. et al. Low- N protein engineering with data-efficient deep learning. Nat. Methods 18 , 389–396 (2021).

Ferruz, N. & Höcker, B. Controllable protein design with language models. Nat. Mach. Intell. 4 , 521–532 (2022).

Hsu, C. et al. Learning inverse folding from millions of predicted structures. In International Conference on Machine Learning 8946–8970 (2022).

Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373 , 871–876 (2021). Inspired by AlphaFold2, this study reported RoseTTAFold, a novel three-track neural module capable of simultaneously processing protein’s sequence, distance and coordinates.

Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28 , 31–36 (1988).

Lin, T.-S. et al. BigSMILES: a structurally-based line notation for describing macromolecules. ACS Cent. Sci. 5 , 1523–1531 (2019).

Krenn, M. et al. SELFIES and the future of molecular string representations. Patterns 3 , 100588 (2022).

Flam-Shepherd, D., Zhu, K. & Aspuru-Guzik, A. Language models can learn complex molecular distributions. Nat. Commun. 13 , 3293 (2022).

Skinnider, M. A. et al. Chemical language models enable navigation in sparsely populated chemical space. Nat. Mach. Intell. 3 , 759–770 (2021).

Chithrananda, S., Grand, G. & Ramsundar, B. ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. In Machine Learning for Molecules Workshop at NeurIPS (2020).

Schwaller, P. et al. Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy. Chem. Sci. 11 , 3316–3325 (2020).

Tetko, I. V. et al. State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis. Nat. Commun. 11 , 5575 (2020).

Schwaller, P. et al. Mapping the space of chemical reactions using attention-based neural networks. Nat. Mach. Intell. 3 , 144–152 (2021).

Kovács, D. P., McCorkindale, W. & Lee, A. A. Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias. Nat. Commun. 12 , 1695 (2021).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Pesciullesi, G. et al. Transfer learning enables the molecular transformer to predict regio-and stereoselective reactions on carbohydrates. Nat. Commun. 11 , 4874 (2020).

Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems 30 , 5998–6008 (2017). This paper introduced the transformer, a modern neural network architecture that can process sequential data in parallel, revolutionizing natural language processing and sequence modeling.

Mousavi, S. M. et al. Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nat. Commun. 11 , 3952 (2020).

Avsec, Ž. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat. Methods 18 , 1196–1203 (2021).

Meier, J. et al. Language models enable zero-shot prediction of the effects of mutations on protein function. In Advances in Neural Information Processing Systems 34 , 29287–29303 (2021).

Kamienny, P.-A. et al. End-to-end symbolic regression with transformers. In Advances in Neural Information Processing Systems 35 , 10269–10281 (2022).

Jaegle, A. et al. Perceiver: general perception with iterative attention. In International Conference on Machine Learning 4651–4664 (2021).

Chen, L. et al. Decision transformer: reinforcement learning via sequence modeling. In Advances in Neural Information Processing Systems 34 , 15084–15097 (2021).

Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In International Conference on Learning Representations (2020).

Choromanski, K. et al. Rethinking attention with performers. In International Conference on Learning Representations (2021).

Li, Z. et al. Fourier neural operator for parametric partial differential equations. In International Conference on Learning Representations (2021).

Kovachki, N. et al. Neural operator: learning maps between function spaces. J. Mach. Learn. Res. 24 , 1–97 (2023).

Russell, J. L. Kepler’s laws of planetary motion: 1609–1666. Br. J. Hist. Sci. 2 , 1–24 (1964).

Huang, K. et al. Artificial intelligence foundation for therapeutic science. Nat. Chem. Biol. 18 , 1033–1036 (2022).

Guimerà, R. et al. A Bayesian machine scientist to aid in the solution of challenging scientific problems. Sci. Adv. 6 , eaav6971 (2020).

Liu, G. et al. Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii. Nat. Chem. Biol. https://doi.org/10.1038/s41589-023-01349-8 (2023).

Gómez-Bombarelli, R. et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nat. Mater. 15 , 1120–1127 (2016). This paper proposes using a black-box AI predictor to accelerate high-throughput screening of molecules in materials science.

Article   ADS   PubMed   Google Scholar  

Sadybekov, A. A. et al. Synthon-based ligand discovery in virtual libraries of over 11 billion compounds. Nature 601 , 452–459 (2022).

The NNPDF Collaboration Evidence for intrinsic charm quarks in the proton. Nature 606 , 483–487 (2022).

Graff, D. E., Shakhnovich, E. I. & Coley, C. W. Accelerating high-throughput virtual screening through molecular pool-based active learning. Chem. Sci. 12 , 7866–7881 (2021).

Janet, J. P. et al. Accurate multiobjective design in a space of millions of transition metal complexes with neural-network-driven efficient global optimization. ACS Cent. Sci. 6 , 513–524 (2020).

Bacon, F. Novum Organon Vol. 1620 (2000).

Schmidt, M. & Lipson, H. Distilling free-form natural laws from experimental data. Science 324 , 81–85 (2009).

Petersen, B. K. et al. Deep symbolic regression: recovering mathematical expressions from data via risk-seeking policy gradients. In International Conference on Learning Representations (2020).

Zhavoronkov, A. et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat. Biotechnol. 37 , 1038–1040 (2019). This paper describes a reinforcement-learning algorithm for navigating molecular combinatorial spaces, and it validates generated molecules using wet-lab experiments.

Zhou, Z. et al. Optimization of molecules via deep reinforcement learning. Sci. Rep. 9 , 10752 (2019).

You, J. et al. Graph convolutional policy network for goal-directed molecular graph generation. In Advances in Neural Information Processing Systems 31 , 6412–6422 (2018).

Bengio, Y. et al. GFlowNet foundations. Preprint at https://arxiv.org/abs/2111.09266 (2021). This paper describes a generative flow network that generates objects by sampling them from a distribution optimized for drug design.

Jain, M. et al. Biological sequence design with GFlowNets. In International Conference on Machine Learning 9786–9801 (2022).

Malkin, N. et al. Trajectory balance: improved credit assignment in GFlowNets. In Advances in Neural Information Processing Systems 35 , 5955–5967 (2022).

Borkowski, O. et al. Large scale active-learning-guided exploration for in vitro protein production optimization. Nat. Commun. 11 , 1872 (2020). This study introduced a dynamic programming approach to determine the optimal locations and capacities of hydropower dams in the Amazon Basin, balancing between energy production and environmental impact .

Flecker, A. S. et al. Reducing adverse impacts of Amazon hydropower expansion. Science 375 , 753–760 (2022). This study introduced a dynamic programming approach to determine the optimal locations and capacities of hydropower dams in the Amazon basin, achieving a balance between the benefits of energy production and the potential environmental impacts.

Pion-Tonachini, L. et al. Learning from learning machines: a new generation of AI technology to meet the needs of science. Preprint at https://arxiv.org/abs/2111.13786 (2021).

Kusner, M. J., Paige, B. & Hernández-Lobato, J. M. Grammar variational autoencoder. In International Conference on Machine Learning 1945–1954 (2017). This paper describes a grammar variational autoencoder that generates novel symbolic laws and drug molecules.

Brunton, S. L., Proctor, J. L. & Kutz, J. N. Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc. Natl Acad. Sci. USA 113 , 3932–3937 (2016).

Article   ADS   MathSciNet   CAS   PubMed   PubMed Central   MATH   Google Scholar  

Liu, Z. & Tegmark, M. Machine learning hidden symmetries. Phys. Rev. Lett. 128 , 180201 (2022).

Article   ADS   MathSciNet   CAS   PubMed   Google Scholar  

Gabbard, H. et al. Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy. Nat. Phys. 18 , 112–117 (2022).

Chen, D. et al. Automating crystal-structure phase mapping by combining deep learning with constraint reasoning. Nat. Mach. Intell. 3 , 812–822 (2021).

Gómez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4 , 268–276 (2018).

Anishchenko, I. et al. De novo protein design by deep network hallucination. Nature 600 , 547–552 (2021).

Fu, T. et al. Differentiable scaffolding tree for molecular optimization. In International Conference on Learning Representations (2021).

Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361 , 360–365 (2018).

Huang, K. et al. Therapeutics Data Commons: machine learning datasets and tasks for drug discovery and development. In NeurIPS Datasets and Benchmarks (2021). This study describes an initiative with open AI models, datasets and education programmes to facilitate advances in therapeutic science across all stages of drug discovery and development.

Dance, A. Lab hazard. Nature 458 , 664–665 (2009).

Segler, M. H. S., Preuss, M. & Waller, M. P. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555 , 604–610 (2018). This paper describes an approach that combines deep neural networks with Monte Carlo tree search to plan chemical synthesis.

Gao, W., Raghavan, P. & Coley, C. W. Autonomous platforms for data-driven organic synthesis. Nat. Commun. 13 , 1075 (2022).

Kusne, A. G. et al. On-the-fly closed-loop materials discovery via Bayesian active learning. Nat. Commun. 11 , 5966 (2020).

Gormley,A. J. & Webb, M. A. Machine learning in combinatorial polymer chemistry. Nat. Rev. Mater. 6 , 642–644 (2021).

Ament, S. et al. Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams. Sci. Adv. 7 , eabg4930 (2021).

Degrave, J. et al. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602 , 414–419 (2022). This paper describes an approach for controlling tokamak plasmas, using a reinforcement-learning agent to command-control coils and satisfy physical and operational constraints.

Melnikov, A. A. et al. Active learning machine learns to create new quantum experiments. Proc. Natl Acad. Sci. USA 115 , 1221–1226 (2018).

Smith, J. S., Isayev, O. & Roitberg, A. E. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 8 , 3192–3203 (2017).

Wang, D. et al. Efficient sampling of high-dimensional free energy landscapes using adaptive reinforced dynamics. Nat. Comput. Sci. 2 , 20–29 (2022). This paper describes a neural network for reliable uncertainty estimations in molecular dynamics, enabling efficient sampling of high-dimensional free energy landscapes.

Wang, W. & Gómez-Bombarelli, R. Coarse-graining auto-encoders for molecular dynamics. npj Comput. Mater. 5 , 125 (2019).

Hermann, J., Schätzle, Z. & Noé, F. Deep-neural-network solution of the electronic Schrödinger equation. Nat. Chem. 12 , 891–897 (2020). This paper describes a method to learn the wavefunction of quantum systems using deep neural networks in conjunction with variational quantum Monte Carlo.

Carleo, G. & Troyer, M. Solving the quantum many-body problem with artificial neural networks. Science 355 , 602–606 (2017).

Em Karniadakis, G. et al. Physics-informed machine learning. Nat. Rev. Phys. 3 , 422–440 (2021).

Li, Z. et al. Physics-informed neural operator for learning partial differential equations. Preprint at https://arxiv.org/abs/2111.03794 (2021).

Kochkov, D. et al. Machine learning–accelerated computational fluid dynamics. Proc. Natl Acad. Sci. USA 118 , e2101784118 (2021). This paper describes an approach to accelerating computational fluid dynamics by training a neural network to interpolate from coarse to fine grids and generalize to varying forcing functions and Reynolds numbers.

Ji, W. et al. Stiff-PINN: physics-informed neural network for stiff chemical kinetics. J. Phys. Chem. A 125 , 8098–8106 (2021).

Smith, J. D., Azizzadenesheli, K. & Ross, Z. E. EikoNet: solving the Eikonal equation with deep neural networks. IEEE Trans. Geosci. Remote Sens. 59 , 10685–10696 (2020).

Waheed, U. B. et al. PINNeik: Eikonal solution using physics-informed neural networks. Comput. Geosci. 155 , 104833 (2021).

Chen, R. T. Q. et al. Neural ordinary differential equations. In Advances in Neural Information Processing Systems 31 , 6572–6583 (2018). This paper established a connection between neural networks and differential equations by introducing the adjoint method to learn continuous-time dynamical systems from data, replacing backpropagation.

Raissi, M., Perdikaris, P. & Karniadakis, G. E. Physics-informed neural networks: a deep learning framework for solving forward and inverse problems involving nonlinear partial differential equations. J. Comput. Phys. 378 , 686–707 (2019). This paper describes a deep-learning approach for solving forwards and inverse problems in nonlinear partial differential equations and can find solutions to differential equations from data.

Article   ADS   MathSciNet   MATH   Google Scholar  

Lu, L. et al. Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators. Nat. Mach. Intell. 3 , 218–229 (2021).

Brandstetter, J., Worrall, D. & Welling, M. Message passing neural PDE solvers. In International Conference on Learning Representations (2022).

Noé, F. et al. Boltzmann generators: sampling equilibrium states of many-body systems with deep learning. Science 365 , eaaw1147 (2019). This paper presents an efficient sampling algorithm using normalizing flows to simulate equilibrium states in many-body systems.

Rezende, D. & Mohamed, S. Variational inference with normalizing flows. In International Conference on Machine Learning 37 , 1530–1538, (2015).

Dinh, L., Sohl-Dickstein, J. & Bengio, S. Density estimation using real NVP. In International Conference on Learning Representations (2017).

Nicoli, K. A. et al. Estimation of thermodynamic observables in lattice field theories with deep generative models. Phys. Rev. Lett. 126 , 032001 (2021).

Kanwar, G. et al. Equivariant flow-based sampling for lattice gauge theory. Phys. Rev. Lett. 125 , 121601 (2020).

Gabrié, M., Rotskoff, G. M. & Vanden-Eijnden, E. Adaptive Monte Carlo augmented with normalizing flows. Proc. Natl Acad. Sci. USA 119 , e2109420119 (2022).

Article   MathSciNet   PubMed   PubMed Central   Google Scholar  

Jasra, A., Holmes, C. C. & Stephens, D. A. Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling. Stat. Sci. 20 , 50–67 (2005).

Bengio, Y. et al. Better mixing via deep representations. In International Conference on Machine Learning 552–560 (2013).

Pompe, E., Holmes, C. & Łatuszyński, K. A framework for adaptive MCMC targeting multimodal distributions. Ann. Stat. 48 , 2930–2952 (2020).

Article   MathSciNet   MATH   Google Scholar  

Townshend, R. J. L. et al. ATOM3D: tasks on molecules in three dimensions. In NeurIPS Datasets and Benchmarks (2021).

Kearnes, S. M. et al. The open reaction database. J. Am. Chem. Soc. 143 , 18820–18826 (2021).

Chanussot, L. et al. Open Catalyst 2020 (OC20) dataset and community challenges. ACS Catal. 11 , 6059–6072 (2021).

Brown, N. et al. GuacaMol: benchmarking models for de novo molecular design. J. Chem. Inf. Model. 59 , 1096–1108 (2019).

Notin, P. et al. Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval. In International Conference on Machine Learning 16990–17017 (2022).

Mitchell, M. et al. Model cards for model reporting. In Conference on Fairness, Accountability, and Transparency 220–229 (2019).

Gebru, T. et al. Datasheets for datasets. Commun. ACM 64 , 86–92 (2021).

Bai, X. et al. Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence. Nat. Mach. Intell. 3 , 1081–1089 (2021).

Warnat-Herresthal, S. et al. Swarm learning for decentralized and confidential clinical machine learning. Nature 594 , 265–270 (2021).

Hie, B., Cho, H. & Berger, B. Realizing private and practical pharmacological collaboration. Science 362 , 347–350 (2018).

Rohrbach, S. et al. Digitization and validation of a chemical synthesis literature database in the ChemPU. Science 377 , 172–180 (2022).

Gysi, D. M. et al. Network medicine framework for identifying drug-repurposing opportunities for COVID-19. Proc. Natl Acad. Sci. USA 118 , e2025581118 (2021).

King, R. D. et al. The automation of science. Science 324 , 85–89 (2009).

Mirdita, M. et al. ColabFold: making protein folding accessible to all. Nat. Methods 19 , 679–682 (2022).

Doerr, S. et al. TorchMD: a deep learning framework for molecular simulations. J. Chem. Theory Comput. 17 , 2355–2363 (2021).

Schoenholz, S. S. & Cubuk, E. D. JAX MD: a framework for differentiable physics. In Advances in Neural Information Processing Systems 33 , 11428–11441 (2020).

Peters, J., Janzing, D. & Schölkopf, B. Elements of Causal Inference: Foundations and Learning Algorithms (MIT Press, 2017).

Bengio, Y. et al. A meta-transfer objective for learning to disentangle causal mechanisms. In International Conference on Learning Representations (2020).

Schölkopf, B. et al. Toward causal representation learning. Proc. IEEE 109 , 612–634 (2021).

Goyal, A. & Bengio, Y. Inductive biases for deep learning of higher-level cognition. Proc. R. Soc. A 478 , 20210068 (2022).

Deleu, T. et al. Bayesian structure learning with generative flow networks. In Conference on Uncertainty in Artificial Intelligence 518–528 (2022).

Geirhos, R. et al. Shortcut learning in deep neural networks. Nat. Mach. Intell. 2 , 665–673 (2020).

Koh, P. W. et al. WILDS: a benchmark of in-the-wild distribution shifts. In International Conference on Machine Learning 5637–5664 (2021).

Luo, Z. et al. Label efficient learning of transferable representations across domains and tasks. In Advances in Neural Information Processing Systems 30 , 165–177 (2017).

Mahmood, R. et al. How much more data do I need? estimating requirements for downstream tasks. In IEEE Conference on Computer Vision and Pattern Recognition 275–284 (2022).

Coley, C. W., Eyke, N. S. & Jensen, K. F. Autonomous discovery in the chemical sciences part II: outlook. Angew. Chem. Int. Ed. 59 , 23414–23436 (2020).

Gao, W. & Coley, C. W. The synthesizability of molecules proposed by generative models. J. Chem. Inf. Model. 60 , 5714–5723 (2020).

Kogler, R. et al. Jet substructure at the Large Hadron Collider. Rev. Mod. Phys. 91 , 045003 (2019).

Acosta, J. N. et al. Multimodal biomedical AI. Nat. Med. 28 , 1773–1784 (2022).

Alayrac, J.-B. et al. Flamingo: a visual language model for few-shot learning. In Advances in Neural Information Processing Systems 35 , 23716–23736 (2022).

Elmarakeby, H. A. et al. Biologically informed deep neural network for prostate cancer discovery. Nature 598 , 348–352 (2021).

Qin, Y. et al. A multi-scale map of cell structure fusing protein images and interactions. Nature 600 , 536–542 (2021).

Schaffer, L. V. & Ideker, T. Mapping the multiscale structure of biological systems. Cell Systems 12 , 622–635 (2021).

Stiglic, G. et al. Interpretability of machine learning-based prediction models in healthcare. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 10 , e1379 (2020).

Erion, G. et al. A cost-aware framework for the development of AI models for healthcare applications. Nat. Biomed. Eng. 6 , 1384–1398 (2022).

Lundberg, S. M. et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat. Biomed. Eng. 2 , 749–760 (2018).

Sanders, L. M. et al. Beyond low Earth orbit: biological research, artificial intelligence, and self-driving labs. Preprint at https://arxiv.org/abs/2112.12582 (2021).

Gagne, D. J. II et al. Interpretable deep learning for spatial analysis of severe hailstorms. Mon. Weather Rev. 147 , 2827–2845 (2019).

Rudin, C. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat. Mach. Intell. 1 , 206–215 (2019).

Koh, P. W. & Liang, P. Understanding black-box predictions via influence functions. In International Conference on Machine Learning 1885–1894 (2017).

Mirzasoleiman, B., Bilmes, J. & Leskovec, J. Coresets for data-efficient training of machine learning models. In International Conference on Machine Learning 6950–6960 (2020).

Kim, B. et al. Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In International Conference on Machine Learning 2668–2677 (2018).

Silver, D. et al. Mastering the game of go without human knowledge. Nature 550 , 354–359 (2017).

Baum, Z. J. et al. Artificial intelligence in chemistry: current trends and future directions. J. Chem. Inf. Model. 61 , 3197–3212 (2021).

Finlayson, S. G. et al. Adversarial attacks on medical machine learning. Science 363 , 1287–1289 (2019).

Urbina, F. et al. Dual use of artificial-intelligence-powered drug discovery. Nat. Mach. Intell. 4 , 189–191 (2022).

Norgeot, B. et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat. Med. 26 , 1320–1324 (2020).

Download references

Acknowledgements

M.Z. gratefully acknowledges the support of the National Institutes of Health under R01HD108794, U.S. Air Force under FA8702-15-D-0001, awards from Harvard Data Science Initiative, Amazon Faculty Research, Google Research Scholar Program, Bayer Early Excellence in Science, AstraZeneca Research, Roche Alliance with Distinguished Scientists, and Kempner Institute for the Study of Natural and Artificial Intelligence. C.P.G. and Y.D. acknowledge the support from the U.S. Air Force Office of Scientific Research under Multidisciplinary University Research Initiatives Program (MURI) FA9550-18-1-0136, Defense University Research Instrumentation Program (DURIP) FA9550-21-1-0316, and awards from Scientific Autonomous Reasoning Agent (SARA), and AI for Discovery Assistant (AIDA). Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the funders. We thank D. Hassabis, A. Davies, S. Mohamed, Z. Li, K. Ma, Z. Qiao, E. Weinstein, A. V. Weller, Y. Zhong and A. M. Brandt for discussions on the paper.

Author information

Hanchen Wang

Present address: Department of Research and Early Development, Genentech Inc, South San Francisco, CA, USA

Present address: Department of Computer Science, Stanford University, Stanford, CA, USA

These authors contributed equally: Hanchen Wang, Tianfan Fu, Yuanqi Du

Authors and Affiliations

Department of Engineering, University of Cambridge, Cambridge, UK

Hanchen Wang & Joan Lasenby

Department of Computing and Mathematical Sciences, California Institute of Technology, Pasadena, CA, USA

Hanchen Wang & Anima Anandkumar

Department of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA

Department of Computer Science, Cornell University, Ithaca, NY, USA

Yuanqi Du & Carla P. Gomes

Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

Wenhao Gao & Connor W. Coley

Department of Computer Science, Stanford University, Stanford, CA, USA

Kexin Huang & Jure Leskovec

Department of Physics, Massachusetts Institute of Technology, Cambridge, MA, USA

Harvard-MIT Program in Health Sciences and Technology, Cambridge, MA, USA

Payal Chandak

Mila – Quebec AI Institute, Montreal, Quebec, Canada

Shengchao Liu, Andreea Deac, Jian Tang & Yoshua Bengio

Université de Montréal, Montreal, Quebec, Canada

Shengchao Liu, Andreea Deac & Yoshua Bengio

Department of Earth, Environmental and Planetary Sciences, Brown University, Providence, RI, USA

Peter Van Katwyk & Karianne Bergen

Data Science Institute, Brown University, Providence, RI, USA

NVIDIA, Santa Clara, CA, USA

Anima Anandkumar

Center for Computational Astrophysics, Flatiron Institute, New York, NY, USA

Department of Astrophysical Sciences, Princeton University, Princeton, NJ, USA

Department of Physics, Carnegie Mellon University, Pittsburgh, PA, USA

Department of Physics and Center for Data Science, New York University, New York, NY, USA

Google DeepMind, London, UK

Pushmeet Kohli & Petar Veličković

Microsoft Research, Beijing, China

Tie-Yan Liu

Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA

Arjun Manrai & Marinka Zitnik

Department of Systems Biology, Harvard Medical School, Boston, MA, USA

Debora Marks

Broad Institute of MIT and Harvard, Cambridge, MA, USA

Debora Marks & Marinka Zitnik

Deep Forest Sciences, Palo Alto, CA, USA

Bharath Ramsundar

BioMap, Beijing, China

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

University of Illinois at Urbana-Champaign, Champaign, IL, USA

HEC Montréal, Montreal, Quebec, Canada

CIFAR AI Chair, Toronto, Ontario, Canada

Department of Computer Science and Technology, University of Cambridge, Cambridge, UK

Petar Veličković

University of Amsterdam, Amsterdam, Netherlands

Max Welling

Microsoft Research Amsterdam, Amsterdam, Netherlands

DP Technology, Beijing, China

Linfeng Zhang

AI for Science Institute, Beijing, China

Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA

Connor W. Coley

Harvard Data Science Initiative, Cambridge, MA, USA

Marinka Zitnik

Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA

You can also search for this author in PubMed   Google Scholar

Contributions

All authors contributed to the design and writing of the paper, helped shape the research, provided critical feedback, and commented on the paper and its revisions. H.W., T.F., Y.D. and M.Z conceived the study and were responsible for overall direction and planning. W.G., K.H. and Z.L. contributed equally to this work (equal second authorship) and are listed alphabetically.

Corresponding author

Correspondence to Marinka Zitnik .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Peer review

Peer review information.

Nature thanks Brian Gallagher and Benjamin Nachman for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article.

Wang, H., Fu, T., Du, Y. et al. Scientific discovery in the age of artificial intelligence. Nature 620 , 47–60 (2023). https://doi.org/10.1038/s41586-023-06221-2

Download citation

Received : 30 March 2022

Accepted : 16 May 2023

Published : 02 August 2023

Issue Date : 03 August 2023

DOI : https://doi.org/10.1038/s41586-023-06221-2

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Antimicrobial resistance crisis: could artificial intelligence be the solution.

• Guang-Yu Liu
• Xiao-Fen Liu

Military Medical Research (2024)

Embracing data science in catalysis research

• Manu Suvarna
• Javier Pérez-Ramírez

Nature Catalysis (2024)

Artificial intelligence to predict soil temperatures by development of novel model

• Lakindu Mampitiya
• Kenjabek Rozumbetov
• Upaka Rathnayake

Scientific Reports (2024)

Automated BigSMILES conversion workflow and dataset for homopolymeric macromolecules

• Joonbum Lee
• Junhee Seok

Scientific Data (2024)

Techniques for supercharging academic writing with generative AI

• Zhicheng Lin

Nature Biomedical Engineering (2024)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

AI for Research

Ai-powered academic research tool.

• Conduct academic research: Search scholarly sources for relevant information and key findings for your research paper or thesis.
• Compile a literature review: Use the tool to find and summarize relevant studies and articles for your literature review.
• Stay updated on recent developments: Keep up-to-date with the latest research and developments in your field of study or profession.
• Prepare for a presentation or lecture: Gather and summarize key information and findings for a presentation or lecture.
• Write a research proposal: Use the tool to identify gaps in the current literature and propose new research questions or hypotheses.

New & Trending Tools

Business model development tutor, identifying business opportunities tutor.

The best AI tools to power your academic research

The future of academia is likely to be transformed by AI language models such as ChatGPT. Here are some other tools worth knowing about.

"ChatGPT will redefine the future of academic research. But most academics don't know how to use it intelligently," Mushtaq Bilal, a postdoctoral researcher at the University of Southern Denmark, posted on X.

Academia and artificial intelligence (AI) are becoming increasingly intertwined, and as AI continues to advance, it is likely that academics will continue to either embrace its potential or voice concerns about its risks.

"There are two camps in academia. The first is the early adopters of artificial intelligence, and the second is the professors and academics who think AI corrupts academic integrity," Bilal told Euronews Next.

• Meet Aitana, Spain's first AI model, who is earning up to €10,000 a month

He places himself firmly in the first camp.

The Pakistani-born and Denmark-based professor believes that if used thoughtfully, AI language models could help democratise education and even give way to more knowledge.

Many experts have pointed out that the accuracy and quality of the output produced by language models such as ChatGPT are not trustworthy. The generated text can sometimes be biased, limited or inaccurate.

But Bilal says that understanding those limitations, paired with the right approach, can make language models "do a lot of quality labour for you," notably for academia.

Incremental prompting to create a 'structure'

To create an academia-worthy structure, Bilal says it is fundamental to master incremental prompting, a technique traditionally used in behavioural therapy and special education.

It involves breaking down complex tasks into smaller, more manageable steps and providing prompts or cues to help the individual complete each one successfully. The prompts then gradually become more complicated.

In behavioural therapy, incremental prompting allows individuals to build their sense of confidence. In language models, it allows for “way more sophisticated answers”.

• AI models can be trained to be deceptive with safety guardrails ‘ineffective', researchers find

In a thread on X (formerly Twitter), Bilal showed how he managed to get ChatGPT to provide a "brilliant outline" for a journal article using incremental prompting.

In his demonstration, Bilal started by asking ChatGPT about specific concepts relevant to his work, then about authors and their ideas, guiding the AI-driven chatbot through the contextual knowledge pertinent to his essay.

"Now that ChatGPT has a fair idea about my project, I ask it to create an outline for a journal article," he explained, before declaring the results he obtained would likely save him "20 hours of labour".

"If I just wrote a paragraph for every point in the outline, I'd have a decent first draft of my article".

Incremental prompting also allows ChatGPT and other AI models to help when it comes to "making education more democratic," Bilal said.

Some people have the luxury of discussing with Harvard or Oxford professors potential academic outlines or angles for scientific papers, "but not everyone does," he explained.

"If I were in Pakistan, I would not have access to Harvard professors but I would still need to brainstorm ideas. So instead, I could use AI apps to have an intelligent conversation and help me formulate my research".

Bilal recently made ChatGPT think and talk like a Stanford professor. Then, to fact-check how authentic the output was, he asked the same questions to a real-life Stanford professor. The results were astonishing.

ChatGPT is only one of the many AI-powered apps you can use for academic writing, or to mimic conversations with renowned academics.

Here are other AI-driven software to help your academic efforts, handpicked by Bilal.

1. Consensus

In Bilal’s own words: "If ChatGPT and Google Scholar got married, their child would be Consensus — an AI-powered search engine".

Consensus looks like most search engines but what sets it apart is that you ask Yes/No questions, to which it provides answers with the consensus of the academic community.

Users can also ask Consensus about the relationship between concepts and about something’s cause and effect. For example: Does immigration improve the economy?

Consensus would reply to that question by stating that most studies have found that immigration generally improves the economy, providing a list of the academic papers it used to arrive at the consensus, and ultimately sharing the summaries of the top articles it analysed.

The AI-powered search engine is only equipped to respond to six topics: economics, sleep, social policy, medicine, and mental health and health supplements.

2. Elicit.org

Elicit, "the AI research assistant" according to its founders, also uses language models to answer questions. Still, its knowledge is solely based on research, enabling "intelligent conversations" and brainstorming with a very knowledgeable and verified source.

The software can also find relevant papers without perfect keyword matches, summarise them and extract key information.

3. Scite.ai

Although language models like ChatGPT are not designed to intentionally deceive, it has been proven they can generate text that is not based on factual information, and include fake citations to papers that don't exist.

But there is an AI-powered app that gives you real citations to actually published papers - Scite.

"This is one of my favourite ones to improve workflows," said Bilal.

Similar to Elicit, upon being asked a question, Scite delivers answers with a detailed list of all the papers cited in the response.

"Also, if I make a claim and that claim has been refuted or corroborated by various people or various journals, Scite gives me the exact number. So this is really very, very powerful".

"If I were to teach any seminar on writing, I would teach how to use this app".

4. Research Rabbit

"Research Rabbit is an incredible tool that FAST-TRACKS your research. Best part: it's FREE. But most academics don't know about it,"  tweeted Bilal.

Called by its founders "the Spotify of research," Research Rabbit allows adding academic papers to "collections".

These collections allow the software to learn about the user’s interests, prompting new relevant recommendations.

Research Rabbit also allows visualising the scholarly network of papers and co-authorships in graphs, so that users can follow the work of a single topic or author and dive deeper into their research.

ChatPDF is an AI-powered app that makes reading and analysing journal articles easier and faster.

"It's like ChatGPT, but for research papers," said Bilal.

Users start by uploading the research paper PDF into the AI software and then start asking it questions.

The app then prepares a short summary of the paper and provides the user with examples of questions that it could answer based on the full article.

What promise does AI hold for the future of research?

The development of AI will be as fundamental "as the creation of the microprocessor, the personal computer, the Internet, and the mobile phone," wrote Bill Gates in the latest post on his personal blog, titled ‘The Age of AI Has Begun’.

"Computers haven’t had the effect on education that many of us in the industry have hoped," he wrote. 

"But I think in the next five to 10 years, AI-driven software will finally deliver on the promise of revolutionising the way people teach and learn".

You might also like

Ex-TikTok executive sues company over alleged gender discrimination

Euroviews. 'Quiet hiring' is silently revolutionising the workplace

Remote worker? Here's why you might not get that promotion or bonus

Find academic sources for your next paper

Finish Your Research in Minutes. Save Your Sleep.

Paste your essay to find, summarize, and add credible sources. (That's something Google Scholar can't do!)

200m+ research papers

Precise search filters

Just paste your essay

Join 10,000+ students saving 100s of hours

See Sourcely in action 👇

Please wait. This may take a minute... 

If it takes longer than a minute, try again.

Text exceeds 300 characters. Click here to upgrade to SourcelyPRO for unlimited characters

Success: Scroll Down to see results

Publications From

Minimum Citations

Include Keywords

Exclude Keywords

Results for...

Publication Year:

Publication Venue:

Edit your papers with Yomu AI

Seamless Transition from Sources to Masterpiece

Congratulations on finding the perfect sources for your academic paper! Now, take the next step towards crafting a flawless masterpiece with Yomu. Our AI writing assistant is your guide to refined, error-free writing. Edit your paper like a pro with real-time feedback and efficient writing tools. From research to writing, Yomu & Sourcely are your all-in-one solution for academic excellence.

Sources about

Discover more sources for your essay today, sources about .

Trusted By Academics From

Why trust us? Because we are trusted by the absolute best academic institutions, including Harvard, MIT, and Stanford, among others

POWERFUL FEATURES  

Fed up with scrolling through pages of search results? Our source-finding tool simplifies the process so you can find your sources quickly and easily.

Paste Your Essay

Simply paste your essay or paragraph and let Sourcely do the rest! 

Get Credible Summaries

Save time and effort by quickly getting a general overview/summary of a source material

Export References

Save time and ensure accuracy by exporting your sourced references in various formats, making citation and bibliography creation a breeze.

F ind Sources

Hit the button, and watch Sourcely find all suitable sources. 

Free PDF Downloads

Sourcely also allows users to download free PDFs of many of the sources it lists.

Advanced Filters

Tailor your source discovery by applying advanced filters, such as publication year, authorship, relevance, and more.

PRICING & PLANS  

Sourcely is an investment in your academic career, but we know that budgets can be tight. That's why we strive to keep wallet-friendly prices, with monthly plans starting at just $9 per month or yearly plans at $87 - affordable for everyone.

Pay Per Use

Sourcelyfree.

• Skip hours of Manual Research!
• Assured Credibility of Sources
• Only UP TO 300 characters :(
• Quality results for 300 characters

SourcelyPRO Monthly

• Quick and Easy Source-finding
• Ease of Pasting your Entire Essay
• Skip Tedious Manual Research!
• Generate Credible Summaries
• PDF Downloads of Sources
• Search Millions of Sources
• Filter by Year of Publication

SourcelyPRO Yearly

• All features of the Monthly plan
• Save 20% Off the Monthly Plan
• One purchase, endless benefits
• Lock it in before price increases!
• Pro Yearly users suggest features
• Equal to $7.25/month

SourcelyPRO 2000 Words

• Skip tedious Manual Research!
• Total of 2,000 words

Trusted by researchers and organizations around the world

Over 10,000 students, researchers, and industry experts use Sourcely

See what they're saying

10,000 students helped

100,000 hours saved

 250,000 sources generated 

• How does it work? Our AI algorithms analyze the text and identify key themes and concepts. Then, it searches through our vast data set to find relevant and reliable sources to support those themes. This makes it easy for you to find the information you need to back up your work.
• Who can use it? Our service is perfect for students, researchers, writers, and anyone else who needs to find reliable sources to support their work. It's a great tool for anyone looking to improve the credibility and quality of their writing.
• How much does it cost? We offer a variety of pricing options to fit your needs. We have a free basic plan that is very limited and for the full experience, we have paid versions. Our monthly plan is £4.99 a month, our yearly plan is £29.99/year.
• What makes this service different from others? Unlike other services that simply provide a list of sources, our AI is able to understand the context of your text and find sources that are truly relevant and reliable. Additionally, our data set is the largest in the world, giving you access to more information than any other service.
• Is it easy to use? Yes, our service is very user-friendly. Simply upload your text, and our AI will take care of the rest. You can then easily sort and filter through the sources it finds to find the information you need.
• How quickly can I expect to get the result? Our service is instant, you will get the result as soon as you upload the text.
• How accurate is the service? Our AI is constantly being trained and refined to ensure the highest level of accuracy. We are always working to improve our algorithms to provide you with the most relevant and reliable sources possible. ​
• Can I use it for any language? Currently, our service supports English language only.
• Is there a customer support? Yes, we have a dedicated customer support team that is available to help you with any questions or issues you may have. You can contact us via email or chat.

Elman Mansimov

Armin Hamrah

Daniel Felix

Software Developer

Welcome to Sourcely! Our AI-powered source finding tool is built by students for students, and this approach allows us to create a tool that truly understands the needs of the academic community. Our student perspective also enables us to stay up-to-date with the latest research and trends, and our collaborative approach ensures that our tool is continually improving and evolving.

Linked research data from idea to impact

Accelerate research discovery, we make finding and interpreting global research data fast and simple..

Dimensions provides a suite of research products and time-saving solutions that connect the dots across the research ecosystem.

You can be confident that you’re not missing anything vital, as we host the largest collection of interconnected global research data and layer it with visual applications to fuel discovery.

Whatever you need to uncover, our platform and solutions can drive your decision-making and propel information discovery, saving you hours of time.

Dimensions Analytics

Find the information you need in millions of publications, patents, datasets, grants, and more, and get an overview of topics, organizations, people, or network profiles.

Dimensions Landscape & Discovery

Horizon scan in seconds, with your own customized landscape analysis dashboard and visually explore publications, grants, patents, and clinical trials within minutes.

Dimensions Perspectives & Insights

Get insights to support research strategy, impact assessment and collaboration analysis. Benchmark against others to identify trends, patterns and opportunities.

Dimensions Expert Identifier

Quickly identify experts with an extensive list of researchers precisely matched to your business, featuring additional analytical information not found anywhere else.

Dimensions Reviewer Finder

Find expert reviewers fast – as you pinpoint reviewers for grant applications or publication manuscripts

Dimensions Research Security

Identify potential risks to your research security, verify disclosures, and review research networks – quickly, efficiently, and thoroughly

Dimensions GBQ

Seamlessly combine Dimensions data with your own private and external datasets to analyze billions of data points in seconds and create actionable insights.

Dimensions API

Stream research data into your workflows without manual intervention and access full text search and data retrieval for use in complex analyses and visualizations

“PLOS relies on Dimensions for baseline data about institutions and their funding sources for agreement discussions but also for internal business analytics”

SARA ROUHI, PLOS

“With Dimensions, I don’t waste my time clicking through and switching between databases to find the answers to my questions.”

AIDAN MORRISON, EMERALD PUBLISHING

“Dimensions is becoming a popular resource across campus and earns high marks for its ease-of-use.”

Donna Axel, University of Colorado

“Dimensions Analytics has a wider coverage than other databases in the space”.

Aruna Rajan, Illumina

“Dimensions has improved the ability of the National Physical Laboratory to do research evaluation and analysis by a factor of 10”

Jenny Wooldridge, National Physical Laboratory

Dimensions webinars

Powering research discovery and interpretation with ai.

Join us for this 30-minute webinar, to find out more about Dimension’s commitment to advancing research and science, and support Open Research initiatives through AI technology. We will present our latest features and products that use AI to make research…

New and Notable Updates for Scholarly Publishers

Discover what’s new and notable for publishers in this on demand webinar. In the session, Tyler Ruse, Director of Publisher Solutions, and Michelle Herbert, Product Engagement Specialist, walk you through exciting new updates and features from Dimensions.

Preparing for Research Security: What Can Academic Institutions Be Doing Right Now?

Research security is under increased scrutiny by governments and funders across the world. In the US, we see provisions for research security in the Chips and Science Act of 2022, the proposed NSPM-33 program requirements, DoD’s Countering Unwanted Foreig…

Featured content

Protecting knowledge: the rising importance of research security.

Institutions are now concerned about research security and tools such as Dimensions Research Security can help institutions bolster research security.

Inform open access publishing strategies and evaluate transformative agreements

How to find and analyze data surrounding authorship and funding in topical areas by country, geography, institution, and funder.

A new approach to prospecting and market mapping

Learn how a commercial team uses Dimensions to drive business growth with prospecting and market mapping.

Sign up for our newsletter

AI Research Tools

Avidnote is an AI-powered research tool that helps you organize, write, and analyze your academic work more efficiently. With this tool, you can easily upload

SciSpace is an AI research assistant that simplifies researching papers through AI-generated explanations and a network showing connections between relevant papers. It aims to automate

BRAiN Assistant

Brain Assistant is an AI-powered tool that offers real-time internet searching along with the ability to create a personalized knowledge base from various sources such

scite is an AI-powered research tool that helps researchers discover and evaluate scientific articles. It analyzes millions of citations and shows how each article has

Instabooks AI

Instabooks AI instantly generates customized textbooks on any topic you want to explore in depth. Simply type a detailed description of the information you want

Ai Summary Generator

Ai Summary Generator is a text summarization tool that can instantly summarize lengthy texts or turn them into bullet point lists. It uses AI to

Otio is an AI-powered research and writing assistant designed to help students, researchers, analysts and professionals alike. It can easily summarize your documents and web

Julius is an AI data analysis tool that helps you visualize, analyze, and get insights from all kinds of data. With Julius, you can simply

Consensus is an AI-powered search engine that helps you find evidence-based answers to your research questions. It intelligently searches through over 200 million scientific papers

GigaBrain is a resourceful search engine that uses AI to scan billions of comments across Reddit and other online communities to find the most useful

SciSummary is an AI-powered tool that uses language models like GPT-3.5 and GPT-4 to automatically summarize lengthy scientific articles and research papers. It’s ideal for

Genei is a research tool that automates the process of summarizing background reading and can also generate blogs, articles, and reports. It allows you to

Discover the latest AI research tools to accelerate your studies and academic research. Search through millions of research papers, summarize articles, view citations, and more.

• Privacy Policy
• Terms & Conditions

Copyright © 2024 EasyWithAI.com

Top AI Tools

• Best Free AI Image Generators
• Best AI Video Editors
• Best AI Meeting Assistants
• Best AI Tools for Students
• Top 5 Free AI Text Generators
• Top 5 AI Image Upscalers

Readers like you help support Easy With AI. When you make a purchase using links on our site, we may earn an affiliate commission at no extra cost to you.

Subscribe to our weekly newsletter for the latest AI tools !

We don’t spam! Read our privacy policy for more info.

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Please check your inbox or spam folder to confirm your subscription. Thank you!

Tackling the most challenging problems in computer science

Our teams aspire to make discoveries that positively impact society. Core to our approach is sharing our research and tools to fuel progress in the field, to help more people more quickly. We regularly publish in academic journals, release projects as open source, and apply research to Google products to benefit users at scale.

Featured research developments

Mitigating aviation’s climate impact with Project Contrails

Consensus and subjectivity of skin tone annotation for ML fairness

A toolkit for transparency in AI dataset documentation

Building better pangenomes to improve the equity of genomics

A set of methods, best practices, and examples for designing with AI

Learn more from our research

Researchers across Google are innovating across many domains. We challenge conventions and reimagine technology so that everyone can benefit.

Publications

Google publishes over 1,000 papers annually. Publishing our work enables us to collaborate and share ideas with, as well as learn from, the broader scientific community.

Research areas

From conducting fundamental research to influencing product development, our research teams have the opportunity to impact technology used by billions of people every day.

Tools and datasets

We make tools and datasets available to the broader research community with the goal of building a more collaborative ecosystem.

Meet the people behind our innovations

Our teams collaborate with the research and academic communities across the world

Partnerships to improve our AI products

Ask a question, get an answer backed by real research

1.2b citation statements extracted and analyzed

187 m articles, book chapters, preprints, and datasets.

Trusted by leading Universities, Publishers, and Corporations across the world.

Read what research articles say about each other

scite is an award-winning platform for discovering and evaluating scientific articles via Smart Citations. Smart Citations allow users to see how a publication has been cited by providing the context of the citation and a classification describing whether it provides supporting or contrasting evidence for the cited claim.

Extracted citations in a report page

Never waste time looking for and evaluating research again.

Our innovative index of Smart Citations powers new features built to make research intuitive and trustworthy for anyone engaging with research.

Search Citation Statements

Find information by searching across a mix of metadata (like titles & abstracts) as well as Citation Statements we indexed from the full-text of research articles.

Create Custom Dashboards

Build and manage collections of articles of interest -- from a manual list, systematic review, or a search -- and get aggregate insights, notifications, and more.

Reference Check

Evaluate how references from your manuscript were used by you or your co-authors to ensure you properly cite high quality references.

Journal Metrics

Explore pre-built journal dashboards to find their publications, top authors, compare yearly scite Index rankings in subject areas, and more.

Large Language Model (LLM) Experience for Researchers

Assistant by scite gives you the power of large language models backed by our unique database of Smart Citations to minimize the risk of hallucinations and improve the quality of information and real references.

Use it to get ideas for search strategies, build reference lists for a new topic you're exploring, get help writing marketing and blog posts, and more.

Assistant is built with observability in mind to help you make more informed decisions about AI generated content.

Here are a few examples to try:

"How many rats live in NYC?"

"How does the structure of a protein affect its function?"

Awards & Press

Trusted by researchers and organizations around the world

Over 650,000 students, researchers, and industry experts use scite

See what they're saying

scite is an incredibly clever tool. The feature that classifies papers on whether they find supporting or contrasting evidence for a particular publication saves so much time. It has become indispensable to me when writing papers and finding related work to cite and read.

Emir Efendić, Ph.D

Maastricht University

As a PhD student, I'm so glad that this exists for my literature searches and papers. Being able to assess what is disputed or affirmed in the literature is how the scientific process is supposed to work, and scite helps me do this more efficiently.

Kathleen C McCormick, Ph.D Student

scite is such an awesome tool! It’s never been easier to place a scientific paper in the context of the wider literature.

Mark Mikkelsen, Ph.D

The Johns Hopkins University School of Medicine

This is a really cool tool. I just tried it out on a paper we wrote on flu/pneumococcal seasonality... really interesting to see the results were affirmed by other studies. I had no idea.

David N. Fisman, Ph.D

University of Toronto

Do better research

Join scite to be a part of a community dedicated to making science more reliable.

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

[email protected]

334 Leonard St

Brooklyn, NY 11211

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Copyright © 2024 scite LLC. All rights reserved.

Made with 💙 for researchers

Part of the Research Solutions Family.

Your Writing Assistant for Research

Unlock Your Research Potential with Jenni AI

Are you an academic researcher seeking assistance in your quest to create remarkable research and scientific papers? Jenni AI is here to empower you, not by doing the work for you, but by enhancing your research process and efficiency. Explore how Jenni AI can elevate your academic writing experience and accelerate your journey toward academic excellence.

Loved by over 1 million academics

Academia's Trusted Companion

Join our academic community and elevate your research journey alongside fellow scholars with Jenni AI.

Effortlessly Ignite Your Research Ideas

Unlock your potential with these standout features

Boost Productivity

Save time and effort with AI assistance, allowing you to focus on critical aspects of your research. Craft well-structured, scholarly papers with ease, backed by AI-driven recommendations and real-time feedback.

Get started

Overcome Writer's Block

Get inspiration and generate ideas to break through the barriers of writer's block. Jenni AI generates research prompts tailored to your subject, sparking your creativity and guiding your research.

Unlock Your Full Writing Potential

Jenni AI is designed to boost your academic writing capabilities, not as a shortcut, but as a tool to help you overcome writer's block and enhance your research papers' quality.

 Ensure Accuracy

Properly format citations and references, ensuring your work meets academic standards. Jenni AI offers accurate and hassle-free citation assistance, including APA, MLA, and Chicago styles.

Our Commitment: Academic Honesty

Jenni AI is committed to upholding academic integrity. Our tool is designed to assist, not replace, your effort in research and writing. We strongly discourage any unethical use. We're dedicated to helping you excel in a responsible and ethical manner.

How it Works

Sign up for free.

To get started, sign up for a free account on Jenni AI's platform.

Prompt Generation

Input your research topic, and Jenni AI generates comprehensive prompts to kickstart your paper.

Research Assistance

Find credible sources, articles, and relevant data with ease through our powerful AI-driven research assistant.

Writing Support

Draft and refine your paper with real-time suggestions for structure, content, and clarity.

Citation & References

Let Jenni AI handle your citations and references in multiple styles, saving you valuable time.

What Our Users Say

Discover how Jenni AI has made a difference in the lives of academics just like you

· Aug 26

I thought AI writing was useless. Then I found Jenni AI, the AI-powered assistant for academic writing. It turned out to be much more advanced than I ever could have imagined. Jenni AI = ChatGPT x 10.

Charlie Cuddy

@sonofgorkhali

· 23 Aug

Love this use of AI to assist with, not replace, writing! Keep crushing it @Davidjpark96 💪

Waqar Younas, PhD

@waqaryofficial

· 6 Apr

4/9 Jenni AI's Outline Builder is a game-changer for organizing your thoughts and structuring your content. Create detailed outlines effortlessly, ensuring your writing is clear and coherent. #OutlineBuilder #WritingTools #JenniAI

I started with Jenni-who & Jenni-what. But now I can't write without Jenni. I love Jenni AI and am amazed to see how far Jenni has come. Kudos to http://Jenni.AI team.

· 28 Jul

Jenni is perfect for writing research docs, SOPs, study projects presentations 👌🏽

Stéphane Prud'homme

http://jenni.ai is awesome and super useful! thanks to @Davidjpark96 and @whoisjenniai fyi @Phd_jeu @DoctoralStories @WriteThatPhD

Frequently asked questions

How much does jenni ai cost, how can jenni ai assist me in writing complex academic papers, can jenni ai handle different types of academic papers, such as essays, research papers, and dissertationss jenni ai maintain the originality of my work, how does artificial intelligence enhance my academic writing with jenni ai.

Can Jenni AI help me structure and write a comprehensive literature review?

Will using Jenni AI improve my overall writing skills?

Can Jenni AI assist with crafting a thesis statement?

What sets Jenni AI apart as an AI-powered writing tool?

Can I trust Jenni AI to help me maintain academic integrity in my work?

Choosing the Right Academic Writing Companion

Get ready to make an informed decision and uncover the key reasons why Jenni AI is your ultimate tool for academic excellence.

Feature Featire

COMPETITORS

Enhanced Writing Style

Jenni AI excels in refining your writing style and enhancing sentence structure to meet academic standards with precision.

Competitors may offer basic grammar checking but often fall short in fine-tuning the nuances of writing style.

Academic Writing Process

Jenni AI streamlines the academic writing process, offering real-time assistance in content generation and thorough proofreading.

Competitors may not provide the same level of support, leaving users to navigate the intricacies of academic writing on their own.

Scientific Writing

Jenni AI is tailored for scientific writing, ensuring the clarity and precision needed in research articles and reports.

Competitors may offer generic writing tools that lack the specialized features required for scientific writing.

Original Content and Academic Integrity

Jenni AI's AI algorithms focus on producing original content while preventing plagiarism, ensuring academic integrity.

Competitors may not provide robust plagiarism checks, potentially compromising academic integrity.

Valuable Tool for Technical Writing

Jenni AI extends its versatility to technical writing, aiding in the creation of clear and concise technical documents.

Some competitors may not be as well-suited for technical writing projects.

User-Friendly Interface

Jenni AI offers an intuitive and user-friendly interface, making it easy for both novice and experienced writers to utilize its features effectively.

Some competitors may have steeper learning curves or complex interfaces, which can be time-consuming and frustrating for users.

Seamless Citation Management

Jenni AI simplifies the citation management process, offering suggestions and templates for various citation styles.

Competitors may not provide the same level of support for correct and consistent citations.

Ready to Revolutionize Your Research Writing?

Sign up for a free Jenni AI account today. Unlock your research potential and experience the difference for yourself. Your journey to academic excellence starts here.

Subscribe to the PwC Newsletter

Join the community, trending research, kan: kolmogorov-arnold networks.

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs).

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

This module converts the generated sequence of images into videos with smooth transitions and consistent subjects that are significantly more stable than the modules based on latent spaces only, especially in the context of long video generation.

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

prometheus-eval/prometheus-eval • 2 May 2024

Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs.

X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design

ericlbuehler/mistral.rs • 11 Feb 2024

Starting with a set of pre-trained LoRA adapters, our gating strategy uses the hidden states to dynamically mix adapted layers, allowing the resulting X-LoRA model to draw upon different capabilities and create never-before-used deep layer-wise combinations to solve tasks.

Improving Diffusion Models for Virtual Try-on

Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity.

Lightplane: Highly-Scalable Components for Neural 3D Fields

Contemporary 3D research, particularly in reconstruction and generation, heavily relies on 2D images for inputs or supervision.

ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

ConsistentID comprises two key components: a multimodal facial prompt generator that combines facial features, corresponding facial descriptions and the overall facial context to enhance precision in facial details, and an ID-preservation network optimized through the facial attention localization strategy, aimed at preserving ID consistency in facial regions.

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Compared to both open-source and proprietary models, InternVL 1. 5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks.

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation.

RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing

2471023025/ralm_survey • 30 Apr 2024

Large Language Models (LLMs) have catalyzed significant advancements in Natural Language Processing (NLP), yet they encounter challenges such as hallucination and the need for domain-specific knowledge.

5 AI tools for students: Use AI to help you study, summarize content, and edit papers

Ace your classes with an AI assist.

• Quizlet Q-Chat
• Google Socratic

I wish these AI tools for students were around when I was in school. Sure, AI tools can't do your homework, write your papers, or take your exams, but they can make your life a lot easier.

With AI, long book chapters can be summarized into quick, easy-to-study bullet points, classes can be recorded and transcribed so you can be laser-focused, and weirdly worded paragraphs can be revised with AI-generated text — and that's just scratching the surface of how AI can help you as a student.

The number of AI-powered services available for students can be overwhelming, so we've rounded up the 5 best AI tools for students.

Best AI tool for editing and summarizing text: Grammarly

Grammarly is easily one of the best AI tools for students because of the wide variety of tasks it can help with. 

The most obvious way Grammarly can help you is with text generation and revision suggestions for emails, cover letters, resumes, and even school assignments. The critical warning is that you should never use AI to completely write a paper from scratch, this is a homework assistant, not something doing your homework for you. Grammarly's AI features are best used as supplemental tools that can help you get started with a tough paragraph, find a new way to say something, or edit your papers after they're written.

A few lesser-known AI features Grammarly offers include summarizing big blocks of text, generating ideas for projects, adjusting your writing tone, and providing helpful writing prompts. You can even use Grammarly to help caption your Instagram posts when you're done with homework.

Grammarly's free account lets you generate text with 100 AI prompts every month, but the premium $12/month (billed annually) option can rewrite full sentences, adjust writing tone, and generate text with 1,000 AI prompts monthly.

Stay in the know with Laptop Mag

Get our in-depth reviews, helpful tips, great deals, and the biggest news stories delivered to your inbox.

Best AI tool for intuitive studying: Quizlet Q-Chat

Most students are already familiar with Quizlet and its virtual sets of flashcards to help you master subjects. But to take your studying game to the next level, you need to check out its AI-powered Q-Chat tutor .

There are multiple ways Q-Chat can help you test your knowledge, including AI-generated quizzes, lessons, conversations, and fun games like two truths and a lie. You can also use Q-Chat to help you learn a new language, but Duolingo is a better AI tool for that purpose.

Quizlet lets you try out Q-Chat conversations with a free account, but to use its full features, you'll need a Quizlet Plus account for $7.99/month or $35.99/year. 

Best AI tool for recording and summarizing classes: Otter.ai

When you try to take notes and listen to your professor at the same time, you can sometimes miss important information. With Otter.ai , you can record the class, get transcripts and summaries, and put all your attention into listening to your teacher.

Otter is an incredibly helpful AI tool for students with ADHD or anyone else who finds it difficult to multitask in class and pay attention. However, it's worth noting that you should get permission from your teacher before recording them with Otter.

If you're an online student, Otter works with Zoom, Google Meet, and Microsoft Teams to record, transcribe, and summarize virtual classes. You can also use Otter to record meetings for group projects to easily keep track of what was talked about and what actions were assigned to everyone.

Best AI tool for explaining concepts: Google Socratic

Socratic by Google is a free AI tool available for Android and iOS that helps explain complex concepts to students with helpful visuals, AI-generated answers to questions, and links to relevant YouTube videos.

The app can help high school and university-level students with basic subjects, including algebra, geometry, trigonometry, biology, chemistry, physics, history, and literature.

Socratic can solve math problems and answer questions, but it shouldn't be used to complete homework for you. Instead, it's a useful AI tool when you're stuck on a problem or you don't understand why you got an answer wrong. Socratic can show you step-by-step explanations, helping prepare you for exams.

Another free tool that can offer in-depth explanations is Bing Chat , a GPT-4-based chatbot. This tool scours the entire internet, so Bing Chat can find answers to more complex questions on various subjects compared to Socratic.

Best AI tool for researching academic papers: Consensus

Consensus is an AI search engine for research that helps students find academic papers and studies. This AI tool is best for college and late-high school students who are starting to write research papers requiring academic sources.

You can type any research question or topic into the Consensus website to find relevant sources, and each pulled source will have pre-populated citations in multiple formats for you to copy and paste into your paper. 

Consensus also paired up with Copilot to bring ChatGPT -type functionality to the service. This means you can tack on a command to your search, like "Group together pro and con cases" or "Explain for an 8-year-old." 

A free Consensus account gives you unlimited searches, unlimited AI-powered filters, and 20 AI credits every month for more powerful features, like GPT-4 Summaries, Consensus Meters, Study Snapshots, and Copilot. For unlimited use of those more powerful features, a premium subscription costs $8.99/month.

MORE FROM LAPTOP MAG FOR STUDENTS

• Best college student discounts and perks
• Best laptop backpacks
• Best laptops for college: Student laptops for every budget and major

World Password Day, created by Intel, sees Google make the biggest waves in 2024

Bill Gates isn't the conductor driving the Microsoft AI train, but he did lay the tracks

You're a bot, and I am too: Internet conspiracy theory is 49.6% true

Most Popular

• 2 Asus Zephyrus G14 vs. Razer Blade 14: Which ultraportable gaming laptop is right for you?
• 3 HP Spectre x360 with Intel Ultra 7 gets $300 price cut in HP sale
• 4 It's been 30 years since Apple released this boldly innovative product
• 5 Lenovo Yoga 7i vs Lenovo Slim 7i: Which Gen 9 Lenovo laptop should you buy?

Special Features

Vendor voice.

Some scientists can't stop using AI to write research papers

If you read about 'meticulous commendable intricacy' there's a chance a boffin had help.

Linguistic and statistical analyses of scientific articles suggest that generative AI may have been used to write an increasing amount of scientific literature.

Two academic papers assert that analyzing word choice in the corpus of science publications reveals an increasing usage of AI for writing research papers. One study , published in March by Andrew Gray of University College London in the UK, suggests at least one percent – 60,000 or more – of all papers published in 2023 were written at least partially by AI.

A second paper published in April by a Stanford University team in the US claims this figure might range between 6.3 and 17.5 percent, depending on the topic.

Both papers looked for certain words that large language models (LLMs) use habitually, such as “intricate,” “pivotal,” and “meticulously." By tracking the use of those words across scientific literature, and comparing this to words that aren't particularly favored by AI, the two studies say they can detect an increasing reliance on machine learning within the scientific publishing community.

In Gray's paper, the use of control words like "red," "conclusion," and "after" changed by a few percent from 2019 to 2023. The same was true of other certain adjectives and adverbs until 2023 (termed the post-LLM year by Gray).

In that year use of the words "meticulous," "commendable," and "intricate," rose by 59, 83, and 117 percent respectively, while their prevalence in scientific literature hardly changed between 2019 and 2022. The word with the single biggest increase in prevalence post-2022 was “meticulously”, up 137 percent.

The Stanford paper found similar phenomena, demonstrating a sudden increase for the words "realm," "showcasing," "intricate," and "pivotal." The former two were used about 80 percent more often than in 2021 and 2022, while the latter two were used around 120 and almost 160 percent more frequently respectively.

• Beyond the hype, AI promises leg up for scientific research
• AI researchers have started reviewing their peers using AI assistance
• Boffins deem Google DeepMind's material discoveries rather shallow
• Turns out AI chatbots are way more persuasive than humans

The researchers also considered word usage statistics in various scientific disciplines. Computer science and electrical engineering were ahead of the pack when it came to using AI-preferred language, while mathematics, physics, and papers published by the journal Nature, only saw increases of between five and 7.5 percent.

The Stanford bods also noted that authors posting more preprints, working in more crowded fields, and writing shorter papers seem to use AI more frequently. Their paper suggests that a general lack of time and a need to write as much as possible encourages the use of LLMs, which can help increase output.

Potentially the next big controversy in the scientific community

Using AI to help in the research process isn't anything new, and lots of boffins are open about utilizing AI to tweak experiments to achieve better results. However, using AI to actually write abstracts and other chunks of papers is very different, because the general expectation is that scientific articles are written by actual humans, not robots, and at least a couple of publishers consider using LLMs to write papers to be scientific misconduct.

Using AI models can be very risky as they often produce inaccurate text, the very thing scientific literature is not supposed to do. AI models can even fabricate quotations and citations, an occurrence that infamously got two New York attorneys in trouble for citing cases ChatGPT had dreamed up.

"Authors who are using LLM-generated text must be pressured to disclose this or to think twice about whether doing so is appropriate in the first place, as a matter of basic research integrity," University College London’s Gray opined.

The Stanford researchers also raised similar concerns, writing that use of generative AI in scientific literature could create "risks to the security and independence of scientific practice." ®

Narrower topics

• Large Language Model
• Machine Learning
• Neural Networks
• Tensor Processing Unit

Broader topics

• Self-driving Car

Send us news

Other stories you might like

With run:ai acquisition, nvidia aims to manage your ai kubes, google search results polluted by buggy ai-written code frustrate coders, intel's neuromorphic 'owl brain' swoops into sandia labs, java thriving after 30 years.

Forget the AI doom and hype, let's make computers useful

Don't rent out that container ship yet: cios and biz buyers view ai pcs with some caution, law prof predicts generative ai will die at the hands of watchdogs, politicians call for ban on 'killer robots' and the curbing of ai weapons, us, japan announce joint ai research projects funded by nvidia, microsoft, others, what's up with alphabet and microsoft lately profits, sales – and ai costs, jensen huang and sam altman among tech chiefs invited to federal ai safety board, intel, ampere show running llms on cpus isn't as crazy as it sounds.

• Advertise with us

Our Websites

• The Next Platform
• Blocks and Files

Your Privacy

• Cookies Policy
• Privacy Policy
• Ts & Cs

Copyright. All rights reserved © 1998–2024

Get science-backed answers as you write with Paperpal's Research feature

What are Scholarly Sources and Where Can You Find Them? 

Scholarly or academic sources of information are typically intended for academic audiences and are primarily based on scientific, evidence-based research and well thought out ideas and theories. They differ from popular or general sources in terms of their formal structure, authority, rigor, and purpose. Scholarly sources are authored by experts whose main purpose is to present research findings. Researchers and academicians typically use scholarly sources as they offer access to a wide array of past work that can be used as references and cited in manuscripts. This is especially crucial given the high level of dependability that scholarly sources provide given that they are peer reviewed in a rigorous manner.  

Table of Contents

6 types of scholarly sources and its importance in academic writing .

• 9 ways to identify and access scholarly sources 
• Where can you find scholarly sources? 
• How to cite scholarly sources in research with Paperpal? 

On the other hand, popular or general sources of information such as magazines and news articles are written for wider and more general audiences. They are mainly written to provide information and to keep readers up to date with current news and developments, to entertain and so on. There is an aspect of research involved but they do not necessarily provide links to citations or sources. Popular sources offer a cross section of views and usually conform to specific ideologies and ways of thinking. 

Common types of scholarly sources include the following: 

• Scholarly books: These are published by a university press or an academic publisher. They also include monographs that synthesize existing research or present new insights and perspectives on a specific subject. 
• Journal articles: These are published in recognized journals after rigorous peer-reviews. 
• Conference publications: These consist of papers presented at a conference or seminar. They focus on cutting edge research and are authored and presented by scholars and researchers. Conference proceedings are a good source to understand about new research in the field even before they are published.   
• Publications issued by government agencies: These include white papers, reports and policy documents issued by research institutions that are tasked with providing the government with accurate data, statistics, and analysis on a wide range of topics. 
• Websites: Some websites are also considered scholarly sources. To determine if it is a scholarly source it is important to check the domain of the page, and see if the contact information of the author or publisher is provided. It is also a good idea to evaluate the recency of the information provided and assess if there is any possible bias. 
• Doctoral theses: Written by PhD students as part of their degree requirements, these scholarly sources provide in-depth research on specific topics, and often contribute new ideas and knowledge to different disciplines. 

Scholarly sources are important in academic writing as it provides academicians and researchers the required stamp of rigor and reliability when writing manuscripts. When you submit your manuscript or article for publishing with adequate scholarly sources, it instantly gives your work much needed credibility and trustworthiness. Similarly, when one cites relevant, important experts or scholarly sources, it provides a certain authority to one’s submission.  

Confirmation bias can be prevented when a researcher or author quotes from scholarly sources. Publications look for papers that cite scholarly sources as they have a legacy that is trusted and also offer views on research topics that are unbiased and original. 

9 ways to identify and access scholarly sources

Academicians and researchers should carefully evaluate the sources to identify whether these are scholarly or popular sources. There are some distinct features that differentiate scholarly sources that help academics identify them, as listed below. 

• Evidence based: Scholarly sources contain data and arguments based on evidence and the information can be verified. A list of references or bibliography is provided in a scholarly publication from which the sources used in it can be verified. 
• Author credentials: For every scholarly source the name of the author or authors with their institutional affiliations are provided together with their qualifications. 
• Publisher: Are academic institutions, university presses or commercial publishers. 
• Target audience: Scholarly publications are intended for academicians, experts, students, researchers, and faculty in the specific or inter-related field. 
• Language: Scholarly sources follow the academic style of writing with the use of discipline specific terminology and academic terms. The language is specialized and not simple.  
• Purpose: The purpose of scholarly sources is to communicate findings of original research studies and advance knowledge in the field of study. 
• Bias: As scholarly publications base their information on evidence and facts, it strives to be free from bias. 
• Structure: Scholarly publications are well structured with an abstract, introduction, literature review, sections on methodology, results, and conclusion. They also contain in-text citations and a list of references or a comprehensive bibliography at the end. 
• Peer review: Scholarly sources generally undergo a strict peer review process. The peer review is conducted by different experts in the field. However, there may be some articles that may be considered scholarly even when these are not peer reviewed.  

Where can you find scholarly sources?

While writing academic and research papers, it is vital to use and cite scholarly sources. In order to access scholarly sources, researchers can use the following ways: 

• Institution’s library: an ideal place to access scholarly sources is your institution’s library. Find out the books, journals, databases that your institution’s library provides access to. 
• Database: you can consult credible research databases. Your institution library may provide access to reliable databases. You can also browse through digital libraries. 
• Reputed publisher: Identify books that are published by press associated with universities and reputed publishing companies as these are considered credible and trustworthy.  
• Peer reviewed articles: Browsing through peer reviewed articles in reputed and high impact journals is also another way to access scholarly sources.  

How to cite scholarly sources in research with Paperpal?  

Researchers typically write by searching for existing information and then conduct their study. They then write their paper, but often discover something new they want to explore. This means going back to find more information to make sure their ideas are well-supported. 

Doing research this way involves looking in many places for information, choosing the best sources, and checking if they are trustworthy. It can be slow and tricky to know what information to trust. On top of that, researchers often need to dig deeper while they write to find opposing viewpoints that make their arguments stronger.  

Paperpal’s new Research feature addresses this challenge head-on and helps writers find answers to their research questions while they write. It gives them clear summaries of scientific information from 250 million research articles and integrates the sources they use to their references. This saves them time and makes sure their work is well-supported by facts.  

When using Paperpal, here’s how you can cite scholarly sources: 

• Research Feature: Once you sign up/log in , you’ll notice that the Research feature in Paperpal has two parts: Search and Citation Library.  
• Search: You can submit your query and get accurate insights from over 250 million research articles with verified sources. 
• Citation Library: Below the AI response, you’ll find references. You can add these references to your Citation Library to keep track of new sources.  
• Citing Sources: You can cite a source using numbers, where each number corresponds to a particular source in the list of references in your text. Alternatively, you can cite using the first/last author of the source mentioned in the list of references. 

Now that you’ve explored what scholarly sources are and where to find them, you’re well on your way to strengthening your research and writing. Remember, using credible sources adds weight to your arguments and demonstrates the depth of your knowledge. 

Don’t be discouraged if navigating scholarly resources feels overwhelming at first. Many universities offer research assistance and librarians who can guide you. Additionally, AI academic writing tools like Paperpal can streamline the process of finding and citing relevant sources. 

Paperpal is a comprehensive AI writing toolkit that helps students and researchers achieve 2x the writing in half the time. It leverages 21+ years of STM experience and insights from millions of research articles to provide in-depth academic writing, language editing, and submission readiness support to help you write better, faster.  

Get accurate academic translations, rewriting support, grammar checks, vocabulary suggestions, and generative AI assistance that delivers human precision at machine speed. Try for free or upgrade to Paperpal Prime starting at US$19 a month to access premium features, including consistency, plagiarism, and 30+ submission readiness checks to help you succeed.  

Experience the future of academic writing – Sign up to Paperpal and start writing for free!  

Related Reads:

• How to Cite Social Media Sources in Academic Writing? 
• How to Paraphrase Research Papers Effectively
• What is a Literature Review? How to Write It (with Examples)
• How to Use Paperpal to Generate Emails & Cover Letters?

How to Write a Hypothesis? Types and Examples 

4 ways paperpal encourages responsible writing with ai, you may also like, measuring academic success: definition & strategies for excellence, what is academic writing: tips for students, why traditional editorial process needs an upgrade, paperpal’s new ai research finder empowers authors to..., what is hedging in academic writing  , how to use ai to enhance your college..., ai + human expertise – a paradigm shift..., how to use paperpal to generate emails &....

Science has an AI problem. This group says they can fix it.

• Christine Clark - [email protected]

Media contact:

Published date, share this:, article content.

AI holds the potential to help doctors find early markers of disease and accelerate research on other important scientific advances. But a growing body of evidence has revealed deep flaws in how machine learning is used in science, a problem that has swept through dozens of fields and implicated thousands of erroneous papers.

Now an interdisciplinary team of 19 researchers that includes Marta Serra-Garcia of the University of California San Diego’s Rady School of Management has published guidelines for the responsible use of machine learning in science.

“When we graduate from traditional statistical methods to machine learning methods, there are a vastly greater number of ways to shoot oneself in the foot,” said Arvind Narayanan , director of Princeton University’s   Center for Information Technology Policy , who led the research team along with Princeton computer scientist Sayash Kapoor. “If we don’t have an intervention to improve our scientific standards and reporting standards when it comes to machine learning-based science, we risk not just one discipline but many different scientific disciplines rediscovering these crises one after another.”

Because machine learning methods are new and used by many different disciplines, it is important to develop guidelines that can ensure the credibility of these methods as their use expands. A paper detailing their guidelines was recently published in the journal Science Advances.

“Many researchers are concerned with the emerging reproducibility crisis in the use of these methods, which could be as serious as the replication crisis that emerged in social psychology more than a decade ago,” Serra-Garcia said, an associate professor of economics and strategy at the Rady School.

The good news is that a simple set of best practices can help resolve this newer crisis before it gets out of hand, according to the authors, who come from computer science, mathematics, social science and health research.

“This is a systematic problem with systematic solutions,” said Kapoor , a graduate student who works with Narayanan and who organized the effort to produce the new consensus-based checklist.

The checklist focuses on ensuring the integrity of research that uses machine learning. Science depends on the ability to independently reproduce results and validate claims. Otherwise, new work cannot be reliably built atop old work, and the entire enterprise collapses. While other researchers have developed checklists that apply to discipline-specific problems, notably in medicine, the new guidelines start with the underlying methods and apply them to any quantitative discipline.

{/exp:typographee}

Marta Serra-Garcia Associate Professor of Economics and Strategy

One of the main takeaways is transparency. The checklist calls on researchers to provide detailed descriptions of each machine learning model, including the code, the data used to train and test the model, the hardware specifications used to produce the results, the experimental design, the project’s goals and any limitations of the study’s findings. The standards are flexible enough to accommodate a wide range of nuance, including private datasets and complex hardware configurations, according to the authors.

While the increased rigor of these new standards might slow the publication of any given study, the authors believe wide adoption of these standards would increase the overall rate of discovery and innovation, potentially by a significant amount.

“What we ultimately care about is the pace of scientific progress,” said sociologist Emily Cantrell , one of the lead authors, who is pursuing her Ph.D. at Princeton. “By making sure the papers that get published are of high quality and that they’re a solid base for future papers to build on, that potentially then speeds up the pace of scientific progress. Focusing on scientific progress itself and not just getting papers out the door is really where our emphasis should be.”

Kapoor concurred. The errors hurt. “At the collective level, it’s just a major time sink,” he said. That time costs money. And that money, once wasted, could have catastrophic downstream effects, limiting the kinds of science that attract funding and investment, tanking ventures that are inadvertently built on faulty science and discouraging countless numbers of young researchers.

In working toward a consensus about what should be included in the guidelines, the authors said they aimed to strike a balance: simple enough to be widely adopted, comprehensive enough to catch as many common mistakes as possible.

They say researchers could adopt the standards to improve their own work; peer reviewers could use the checklist to assess papers; and journals could adopt the standards as a requirement for publication.

“The scientific literature, especially in applied machine learning research, is full of avoidable errors,” Narayanan said. “And we want to help people. We want to keep honest people honest.”

The paper, “ Consensus-based recommendations for machine-learning-based science ,” published on May 1 in Science Advances, included the following authors: Sayash Kapoor, Princeton University; Emily Cantrell, Princeton University; Kenny Peng, Cornell University; Thanh Hien (Hien) Pham, Princeton University; Christopher A. Bail, Duke University; Odd Erik Gundersen, Norwegian University of Science and Technology; Jake M. Hofman, Microsoft Research; Jessica Hullman, Northwestern University; Michael A. Lones, Heriot-Watt University; Momin M. Malik, Center for Digital Health, Mayo Clinic; Priyanka Nanayakkara, Northwestern; Russell A. Poldrack, Stanford University; Inioluwa Deborah Raji, University of California-Berkeley; Michael Roberts, University of Cambridge; Matthew J. Salganik, Princeton University; Marta Serra-Garcia, University of California-San Diego; Brandon M. Stewart, Princeton University; Gilles Vandewiele, Ghent University; and Arvind Narayanan, Princeton University.

— Adapted from a Princeton University release

Learn more about research and education at UC San Diego in: Artificial Intelligence

You May Also Like

Ddt pollutants found in deep sea fish off los angeles coast, simulated chemistry: new ai platform designs tomorrow’s cancer drugs, an update from chancellor pradeep k. khosla, new grant supports multi-uc campus effort to build network of open source program offices, stay in the know.

Keep up with all the latest from UC San Diego. Subscribe to the newsletter today.

You have been successfully subscribed to the UC San Diego Today Newsletter.

Campus & Community

Arts & culture, visual storytelling.

• Media Resources & Contacts

Signup to get the latest UC San Diego newsletters delivered to your inbox.

Award-winning publication highlighting the distinction, prestige and global impact of UC San Diego.

Popular Searches: Covid-19   Ukraine   Campus & Community   Arts & Culture   Voices

• Open access
• Published: 18 April 2024

Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research

• James Shaw 1 , 13 ,
• Joseph Ali 2 , 3 ,
• Caesar A. Atuire 4 , 5 ,
• Phaik Yeong Cheah 6 ,
• Armando Guio Español 7 ,
• Judy Wawira Gichoya 8 ,
• Adrienne Hunt 9 ,
• Daudi Jjingo 10 ,
• Katherine Littler 9 ,
• Daniela Paolotti 11 &
• Effy Vayena 12  

BMC Medical Ethics volume  25 , Article number:  46 ( 2024 ) Cite this article

1392 Accesses

6 Altmetric

Metrics details

The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice. In this paper we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022.

The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, research ethics committee members and other actors to engage with challenges and opportunities specifically related to research ethics. In 2022 the focus of the GFBR was “Ethics of AI in Global Health Research”. The forum consisted of 6 case study presentations, 16 governance presentations, and a series of small group and large group discussions. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. In this paper, we highlight central insights arising from GFBR 2022.

We describe the significance of four thematic insights arising from the forum: (1) Appropriateness of building AI, (2) Transferability of AI systems, (3) Accountability for AI decision-making and outcomes, and (4) Individual consent. We then describe eight recommendations for governance leaders to enhance the ethical governance of AI in global health research, addressing issues such as AI impact assessments, environmental values, and fair partnerships.

Conclusions

The 2022 Global Forum on Bioethics in Research illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

Peer Review reports

Introduction

The ethical governance of Artificial Intelligence (AI) in health care and public health continues to be an urgent issue for attention in policy, research, and practice [ 1 , 2 , 3 ]. Beyond the growing number of AI applications being implemented in health care, capabilities of AI models such as Large Language Models (LLMs) expand the potential reach and significance of AI technologies across health-related fields [ 4 , 5 ]. Discussion about effective, ethical governance of AI technologies has spanned a range of governance approaches, including government regulation, organizational decision-making, professional self-regulation, and research ethics review [ 6 , 7 , 8 ]. In this paper, we report on central themes related to challenges and strategies for promoting ethics in research involving AI in global health research, arising from the Global Forum on Bioethics in Research (GFBR), held in Cape Town, South Africa in November 2022. Although applications of AI for research, health care, and public health are diverse and advancing rapidly, the insights generated at the forum remain highly relevant from a global health perspective. After summarizing important context for work in this domain, we highlight categories of ethical issues emphasized at the forum for attention from a research ethics perspective internationally. We then outline strategies proposed for research, innovation, and governance to support more ethical AI for global health.

In this paper, we adopt the definition of AI systems provided by the Organization for Economic Cooperation and Development (OECD) as our starting point. Their definition states that an AI system is “a machine-based system that can, for a given set of human-defined objectives, make predictions, recommendations, or decisions influencing real or virtual environments. AI systems are designed to operate with varying levels of autonomy” [ 9 ]. The conceptualization of an algorithm as helping to constitute an AI system, along with hardware, other elements of software, and a particular context of use, illustrates the wide variety of ways in which AI can be applied. We have found it useful to differentiate applications of AI in research as those classified as “AI systems for discovery” and “AI systems for intervention”. An AI system for discovery is one that is intended to generate new knowledge, for example in drug discovery or public health research in which researchers are seeking potential targets for intervention, innovation, or further research. An AI system for intervention is one that directly contributes to enacting an intervention in a particular context, for example informing decision-making at the point of care or assisting with accuracy in a surgical procedure.

The mandate of the GFBR is to take a broad view of what constitutes research and its regulation in global health, with special attention to bioethics in Low- and Middle- Income Countries. AI as a group of technologies demands such a broad view. AI development for health occurs in a variety of environments, including universities and academic health sciences centers where research ethics review remains an important element of the governance of science and innovation internationally [ 10 , 11 ]. In these settings, research ethics committees (RECs; also known by different names such as Institutional Review Boards or IRBs) make decisions about the ethical appropriateness of projects proposed by researchers and other institutional members, ultimately determining whether a given project is allowed to proceed on ethical grounds [ 12 ].

However, research involving AI for health also takes place in large corporations and smaller scale start-ups, which in some jurisdictions fall outside the scope of research ethics regulation. In the domain of AI, the question of what constitutes research also becomes blurred. For example, is the development of an algorithm itself considered a part of the research process? Or only when that algorithm is tested under the formal constraints of a systematic research methodology? In this paper we take an inclusive view, in which AI development is included in the definition of research activity and within scope for our inquiry, regardless of the setting in which it takes place. This broad perspective characterizes the approach to “research ethics” we take in this paper, extending beyond the work of RECs to include the ethical analysis of the wide range of activities that constitute research as the generation of new knowledge and intervention in the world.

Ethical governance of AI in global health

The ethical governance of AI for global health has been widely discussed in recent years. The World Health Organization (WHO) released its guidelines on ethics and governance of AI for health in 2021, endorsing a set of six ethical principles and exploring the relevance of those principles through a variety of use cases. The WHO guidelines also provided an overview of AI governance, defining governance as covering “a range of steering and rule-making functions of governments and other decision-makers, including international health agencies, for the achievement of national health policy objectives conducive to universal health coverage.” (p. 81) The report usefully provided a series of recommendations related to governance of seven domains pertaining to AI for health: data, benefit sharing, the private sector, the public sector, regulation, policy observatories/model legislation, and global governance. The report acknowledges that much work is yet to be done to advance international cooperation on AI governance, especially related to prioritizing voices from Low- and Middle-Income Countries (LMICs) in global dialogue.

One important point emphasized in the WHO report that reinforces the broader literature on global governance of AI is the distribution of responsibility across a wide range of actors in the AI ecosystem. This is especially important to highlight when focused on research for global health, which is specifically about work that transcends national borders. Alami et al. (2020) discussed the unique risks raised by AI research in global health, ranging from the unavailability of data in many LMICs required to train locally relevant AI models to the capacity of health systems to absorb new AI technologies that demand the use of resources from elsewhere in the system. These observations illustrate the need to identify the unique issues posed by AI research for global health specifically, and the strategies that can be employed by all those implicated in AI governance to promote ethically responsible use of AI in global health research.

RECs and the regulation of research involving AI

RECs represent an important element of the governance of AI for global health research, and thus warrant further commentary as background to our paper. Despite the importance of RECs, foundational questions have been raised about their capabilities to accurately understand and address ethical issues raised by studies involving AI. Rahimzadeh et al. (2023) outlined how RECs in the United States are under-prepared to align with recent federal policy requiring that RECs review data sharing and management plans with attention to the unique ethical issues raised in AI research for health [ 13 ]. Similar research in South Africa identified variability in understanding of existing regulations and ethical issues associated with health-related big data sharing and management among research ethics committee members [ 14 , 15 ]. The effort to address harms accruing to groups or communities as opposed to individuals whose data are included in AI research has also been identified as a unique challenge for RECs [ 16 , 17 ]. Doerr and Meeder (2022) suggested that current regulatory frameworks for research ethics might actually prevent RECs from adequately addressing such issues, as they are deemed out of scope of REC review [ 16 ]. Furthermore, research in the United Kingdom and Canada has suggested that researchers using AI methods for health tend to distinguish between ethical issues and social impact of their research, adopting an overly narrow view of what constitutes ethical issues in their work [ 18 ].

The challenges for RECs in adequately addressing ethical issues in AI research for health care and public health exceed a straightforward survey of ethical considerations. As Ferretti et al. (2021) contend, some capabilities of RECs adequately cover certain issues in AI-based health research, such as the common occurrence of conflicts of interest where researchers who accept funds from commercial technology providers are implicitly incentivized to produce results that align with commercial interests [ 12 ]. However, some features of REC review require reform to adequately meet ethical needs. Ferretti et al. outlined weaknesses of RECs that are longstanding and those that are novel to AI-related projects, proposing a series of directions for development that are regulatory, procedural, and complementary to REC functionality. The work required on a global scale to update the REC function in response to the demands of research involving AI is substantial.

These issues take greater urgency in the context of global health [ 19 ]. Teixeira da Silva (2022) described the global practice of “ethics dumping”, where researchers from high income countries bring ethically contentious practices to RECs in low-income countries as a strategy to gain approval and move projects forward [ 20 ]. Although not yet systematically documented in AI research for health, risk of ethics dumping in AI research is high. Evidence is already emerging of practices of “health data colonialism”, in which AI researchers and developers from large organizations in high-income countries acquire data to build algorithms in LMICs to avoid stricter regulations [ 21 ]. This specific practice is part of a larger collection of practices that characterize health data colonialism, involving the broader exploitation of data and the populations they represent primarily for commercial gain [ 21 , 22 ]. As an additional complication, AI algorithms trained on data from high-income contexts are unlikely to apply in straightforward ways to LMIC settings [ 21 , 23 ]. In the context of global health, there is widespread acknowledgement about the need to not only enhance the knowledge base of REC members about AI-based methods internationally, but to acknowledge the broader shifts required to encourage their capabilities to more fully address these and other ethical issues associated with AI research for health [ 8 ].

Although RECs are an important part of the story of the ethical governance of AI for global health research, they are not the only part. The responsibilities of supra-national entities such as the World Health Organization, national governments, organizational leaders, commercial AI technology providers, health care professionals, and other groups continue to be worked out internationally. In this context of ongoing work, examining issues that demand attention and strategies to address them remains an urgent and valuable task.

The GFBR is an annual meeting organized by the World Health Organization and supported by the Wellcome Trust, the US National Institutes of Health, the UK Medical Research Council (MRC) and the South African MRC. The forum aims to bring together ethicists, researchers, policymakers, REC members and other actors to engage with challenges and opportunities specifically related to research ethics. Each year the GFBR meeting includes a series of case studies and keynotes presented in plenary format to an audience of approximately 100 people who have applied and been competitively selected to attend, along with small-group breakout discussions to advance thinking on related issues. The specific topic of the forum changes each year, with past topics including ethical issues in research with people living with mental health conditions (2021), genome editing (2019), and biobanking/data sharing (2018). The forum is intended to remain grounded in the practical challenges of engaging in research ethics, with special interest in low resource settings from a global health perspective. A post-meeting fellowship scheme is open to all LMIC participants, providing a unique opportunity to apply for funding to further explore and address the ethical challenges that are identified during the meeting.

In 2022, the focus of the GFBR was “Ethics of AI in Global Health Research”. The forum consisted of 6 case study presentations (both short and long form) reporting on specific initiatives related to research ethics and AI for health, and 16 governance presentations (both short and long form) reporting on actual approaches to governing AI in different country settings. A keynote presentation from Professor Effy Vayena addressed the topic of the broader context for AI ethics in a rapidly evolving field. A total of 87 participants attended the forum from 31 countries around the world, representing disciplines of bioethics, AI, health policy, health professional practice, research funding, and bioinformatics. The 2-day forum addressed a wide range of themes. The conference report provides a detailed overview of each of the specific topics addressed while a policy paper outlines the cross-cutting themes (both documents are available at the GFBR website: https://www.gfbr.global/past-meetings/16th-forum-cape-town-south-africa-29-30-november-2022/ ). As opposed to providing a detailed summary in this paper, we aim to briefly highlight central issues raised, solutions proposed, and the challenges facing the research ethics community in the years to come.

In this way, our primary aim in this paper is to present a synthesis of the challenges and opportunities raised at the GFBR meeting and in the planning process, followed by our reflections as a group of authors on their significance for governance leaders in the coming years. We acknowledge that the views represented at the meeting and in our results are a partial representation of the universe of views on this topic; however, the GFBR leadership invested a great deal of resources in convening a deeply diverse and thoughtful group of researchers and practitioners working on themes of bioethics related to AI for global health including those based in LMICs. We contend that it remains rare to convene such a strong group for an extended time and believe that many of the challenges and opportunities raised demand attention for more ethical futures of AI for health. Nonetheless, our results are primarily descriptive and are thus not explicitly grounded in a normative argument. We make effort in the Discussion section to contextualize our results by describing their significance and connecting them to broader efforts to reform global health research and practice.

Uniquely important ethical issues for AI in global health research

Presentations and group dialogue over the course of the forum raised several issues for consideration, and here we describe four overarching themes for the ethical governance of AI in global health research. Brief descriptions of each issue can be found in Table  1 . Reports referred to throughout the paper are available at the GFBR website provided above.

The first overarching thematic issue relates to the appropriateness of building AI technologies in response to health-related challenges in the first place. Case study presentations referred to initiatives where AI technologies were highly appropriate, such as in ear shape biometric identification to more accurately link electronic health care records to individual patients in Zambia (Alinani Simukanga). Although important ethical issues were raised with respect to privacy, trust, and community engagement in this initiative, the AI-based solution was appropriately matched to the challenge of accurately linking electronic records to specific patient identities. In contrast, forum participants raised questions about the appropriateness of an initiative using AI to improve the quality of handwashing practices in an acute care hospital in India (Niyoshi Shah), which led to gaming the algorithm. Overall, participants acknowledged the dangers of techno-solutionism, in which AI researchers and developers treat AI technologies as the most obvious solutions to problems that in actuality demand much more complex strategies to address [ 24 ]. However, forum participants agreed that RECs in different contexts have differing degrees of power to raise issues of the appropriateness of an AI-based intervention.

The second overarching thematic issue related to whether and how AI-based systems transfer from one national health context to another. One central issue raised by a number of case study presentations related to the challenges of validating an algorithm with data collected in a local environment. For example, one case study presentation described a project that would involve the collection of personally identifiable data for sensitive group identities, such as tribe, clan, or religion, in the jurisdictions involved (South Africa, Nigeria, Tanzania, Uganda and the US; Gakii Masunga). Doing so would enable the team to ensure that those groups were adequately represented in the dataset to ensure the resulting algorithm was not biased against specific community groups when deployed in that context. However, some members of these communities might desire to be represented in the dataset, whereas others might not, illustrating the need to balance autonomy and inclusivity. It was also widely recognized that collecting these data is an immense challenge, particularly when historically oppressive practices have led to a low-trust environment for international organizations and the technologies they produce. It is important to note that in some countries such as South Africa and Rwanda, it is illegal to collect information such as race and tribal identities, re-emphasizing the importance for cultural awareness and avoiding “one size fits all” solutions.

The third overarching thematic issue is related to understanding accountabilities for both the impacts of AI technologies and governance decision-making regarding their use. Where global health research involving AI leads to longer-term harms that might fall outside the usual scope of issues considered by a REC, who is to be held accountable, and how? This question was raised as one that requires much further attention, with law being mixed internationally regarding the mechanisms available to hold researchers, innovators, and their institutions accountable over the longer term. However, it was recognized in breakout group discussion that many jurisdictions are developing strong data protection regimes related specifically to international collaboration for research involving health data. For example, Kenya’s Data Protection Act requires that any internationally funded projects have a local principal investigator who will hold accountability for how data are shared and used [ 25 ]. The issue of research partnerships with commercial entities was raised by many participants in the context of accountability, pointing toward the urgent need for clear principles related to strategies for engagement with commercial technology companies in global health research.

The fourth and final overarching thematic issue raised here is that of consent. The issue of consent was framed by the widely shared recognition that models of individual, explicit consent might not produce a supportive environment for AI innovation that relies on the secondary uses of health-related datasets to build AI algorithms. Given this recognition, approaches such as community oversight of health data uses were suggested as a potential solution. However, the details of implementing such community oversight mechanisms require much further attention, particularly given the unique perspectives on health data in different country settings in global health research. Furthermore, some uses of health data do continue to require consent. One case study of South Africa, Nigeria, Kenya, Ethiopia and Uganda suggested that when health data are shared across borders, individual consent remains necessary when data is transferred from certain countries (Nezerith Cengiz). Broader clarity is necessary to support the ethical governance of health data uses for AI in global health research.

Recommendations for ethical governance of AI in global health research

Dialogue at the forum led to a range of suggestions for promoting ethical conduct of AI research for global health, related to the various roles of actors involved in the governance of AI research broadly defined. The strategies are written for actors we refer to as “governance leaders”, those people distributed throughout the AI for global health research ecosystem who are responsible for ensuring the ethical and socially responsible conduct of global health research involving AI (including researchers themselves). These include RECs, government regulators, health care leaders, health professionals, corporate social accountability officers, and others. Enacting these strategies would bolster the ethical governance of AI for global health more generally, enabling multiple actors to fulfill their roles related to governing research and development activities carried out across multiple organizations, including universities, academic health sciences centers, start-ups, and technology corporations. Specific suggestions are summarized in Table  2 .

First, forum participants suggested that governance leaders including RECs, should remain up to date on recent advances in the regulation of AI for health. Regulation of AI for health advances rapidly and takes on different forms in jurisdictions around the world. RECs play an important role in governance, but only a partial role; it was deemed important for RECs to acknowledge how they fit within a broader governance ecosystem in order to more effectively address the issues within their scope. Not only RECs but organizational leaders responsible for procurement, researchers, and commercial actors should all commit to efforts to remain up to date about the relevant approaches to regulating AI for health care and public health in jurisdictions internationally. In this way, governance can more adequately remain up to date with advances in regulation.

Second, forum participants suggested that governance leaders should focus on ethical governance of health data as a basis for ethical global health AI research. Health data are considered the foundation of AI development, being used to train AI algorithms for various uses [ 26 ]. By focusing on ethical governance of health data generation, sharing, and use, multiple actors will help to build an ethical foundation for AI development among global health researchers.

Third, forum participants believed that governance processes should incorporate AI impact assessments where appropriate. An AI impact assessment is the process of evaluating the potential effects, both positive and negative, of implementing an AI algorithm on individuals, society, and various stakeholders, generally over time frames specified in advance of implementation [ 27 ]. Although not all types of AI research in global health would warrant an AI impact assessment, this is especially relevant for those studies aiming to implement an AI system for intervention into health care or public health. Organizations such as RECs can use AI impact assessments to boost understanding of potential harms at the outset of a research project, encouraging researchers to more deeply consider potential harms in the development of their study.

Fourth, forum participants suggested that governance decisions should incorporate the use of environmental impact assessments, or at least the incorporation of environment values when assessing the potential impact of an AI system. An environmental impact assessment involves evaluating and anticipating the potential environmental effects of a proposed project to inform ethical decision-making that supports sustainability [ 28 ]. Although a relatively new consideration in research ethics conversations [ 29 ], the environmental impact of building technologies is a crucial consideration for the public health commitment to environmental sustainability. Governance leaders can use environmental impact assessments to boost understanding of potential environmental harms linked to AI research projects in global health over both the shorter and longer terms.

Fifth, forum participants suggested that governance leaders should require stronger transparency in the development of AI algorithms in global health research. Transparency was considered essential in the design and development of AI algorithms for global health to ensure ethical and accountable decision-making throughout the process. Furthermore, whether and how researchers have considered the unique contexts into which such algorithms may be deployed can be surfaced through stronger transparency, for example in describing what primary considerations were made at the outset of the project and which stakeholders were consulted along the way. Sharing information about data provenance and methods used in AI development will also enhance the trustworthiness of the AI-based research process.

Sixth, forum participants suggested that governance leaders can encourage or require community engagement at various points throughout an AI project. It was considered that engaging patients and communities is crucial in AI algorithm development to ensure that the technology aligns with community needs and values. However, participants acknowledged that this is not a straightforward process. Effective community engagement requires lengthy commitments to meeting with and hearing from diverse communities in a given setting, and demands a particular set of skills in communication and dialogue that are not possessed by all researchers. Encouraging AI researchers to begin this process early and build long-term partnerships with community members is a promising strategy to deepen community engagement in AI research for global health. One notable recommendation was that research funders have an opportunity to incentivize and enable community engagement with funds dedicated to these activities in AI research in global health.

Seventh, forum participants suggested that governance leaders can encourage researchers to build strong, fair partnerships between institutions and individuals across country settings. In a context of longstanding imbalances in geopolitical and economic power, fair partnerships in global health demand a priori commitments to share benefits related to advances in medical technologies, knowledge, and financial gains. Although enforcement of this point might be beyond the remit of RECs, commentary will encourage researchers to consider stronger, fairer partnerships in global health in the longer term.

Eighth, it became evident that it is necessary to explore new forms of regulatory experimentation given the complexity of regulating a technology of this nature. In addition, the health sector has a series of particularities that make it especially complicated to generate rules that have not been previously tested. Several participants highlighted the desire to promote spaces for experimentation such as regulatory sandboxes or innovation hubs in health. These spaces can have several benefits for addressing issues surrounding the regulation of AI in the health sector, such as: (i) increasing the capacities and knowledge of health authorities about this technology; (ii) identifying the major problems surrounding AI regulation in the health sector; (iii) establishing possibilities for exchange and learning with other authorities; (iv) promoting innovation and entrepreneurship in AI in health; and (vi) identifying the need to regulate AI in this sector and update other existing regulations.

Ninth and finally, forum participants believed that the capabilities of governance leaders need to evolve to better incorporate expertise related to AI in ways that make sense within a given jurisdiction. With respect to RECs, for example, it might not make sense for every REC to recruit a member with expertise in AI methods. Rather, it will make more sense in some jurisdictions to consult with members of the scientific community with expertise in AI when research protocols are submitted that demand such expertise. Furthermore, RECs and other approaches to research governance in jurisdictions around the world will need to evolve in order to adopt the suggestions outlined above, developing processes that apply specifically to the ethical governance of research using AI methods in global health.

Research involving the development and implementation of AI technologies continues to grow in global health, posing important challenges for ethical governance of AI in global health research around the world. In this paper we have summarized insights from the 2022 GFBR, focused specifically on issues in research ethics related to AI for global health research. We summarized four thematic challenges for governance related to AI in global health research and nine suggestions arising from presentations and dialogue at the forum. In this brief discussion section, we present an overarching observation about power imbalances that frames efforts to evolve the role of governance in global health research, and then outline two important opportunity areas as the field develops to meet the challenges of AI in global health research.

Dialogue about power is not unfamiliar in global health, especially given recent contributions exploring what it would mean to de-colonize global health research, funding, and practice [ 30 , 31 ]. Discussions of research ethics applied to AI research in global health contexts are deeply infused with power imbalances. The existing context of global health is one in which high-income countries primarily located in the “Global North” charitably invest in projects taking place primarily in the “Global South” while recouping knowledge, financial, and reputational benefits [ 32 ]. With respect to AI development in particular, recent examples of digital colonialism frame dialogue about global partnerships, raising attention to the role of large commercial entities and global financial capitalism in global health research [ 21 , 22 ]. Furthermore, the power of governance organizations such as RECs to intervene in the process of AI research in global health varies widely around the world, depending on the authorities assigned to them by domestic research governance policies. These observations frame the challenges outlined in our paper, highlighting the difficulties associated with making meaningful change in this field.

Despite these overarching challenges of the global health research context, there are clear strategies for progress in this domain. Firstly, AI innovation is rapidly evolving, which means approaches to the governance of AI for health are rapidly evolving too. Such rapid evolution presents an important opportunity for governance leaders to clarify their vision and influence over AI innovation in global health research, boosting the expertise, structure, and functionality required to meet the demands of research involving AI. Secondly, the research ethics community has strong international ties, linked to a global scholarly community that is committed to sharing insights and best practices around the world. This global community can be leveraged to coordinate efforts to produce advances in the capabilities and authorities of governance leaders to meaningfully govern AI research for global health given the challenges summarized in our paper.

Limitations

Our paper includes two specific limitations that we address explicitly here. First, it is still early in the lifetime of the development of applications of AI for use in global health, and as such, the global community has had limited opportunity to learn from experience. For example, there were many fewer case studies, which detail experiences with the actual implementation of an AI technology, submitted to GFBR 2022 for consideration than was expected. In contrast, there were many more governance reports submitted, which detail the processes and outputs of governance processes that anticipate the development and dissemination of AI technologies. This observation represents both a success and a challenge. It is a success that so many groups are engaging in anticipatory governance of AI technologies, exploring evidence of their likely impacts and governing technologies in novel and well-designed ways. It is a challenge that there is little experience to build upon of the successful implementation of AI technologies in ways that have limited harms while promoting innovation. Further experience with AI technologies in global health will contribute to revising and enhancing the challenges and recommendations we have outlined in our paper.

Second, global trends in the politics and economics of AI technologies are evolving rapidly. Although some nations are advancing detailed policy approaches to regulating AI more generally, including for uses in health care and public health, the impacts of corporate investments in AI and political responses related to governance remain to be seen. The excitement around large language models (LLMs) and large multimodal models (LMMs) has drawn deeper attention to the challenges of regulating AI in any general sense, opening dialogue about health sector-specific regulations. The direction of this global dialogue, strongly linked to high-profile corporate actors and multi-national governance institutions, will strongly influence the development of boundaries around what is possible for the ethical governance of AI for global health. We have written this paper at a point when these developments are proceeding rapidly, and as such, we acknowledge that our recommendations will need updating as the broader field evolves.

Ultimately, coordination and collaboration between many stakeholders in the research ethics ecosystem will be necessary to strengthen the ethical governance of AI in global health research. The 2022 GFBR illustrated several innovations in ethical governance of AI for global health research, as well as several areas in need of urgent attention internationally. This summary is intended to inform international and domestic efforts to strengthen research ethics and support the evolution of governance leadership to meet the demands of AI in global health research.

Data availability

All data and materials analyzed to produce this paper are available on the GFBR website: https://www.gfbr.global/past-meetings/16th-forum-cape-town-south-africa-29-30-november-2022/ .

Clark P, Kim J, Aphinyanaphongs Y, Marketing, Food US. Drug Administration Clearance of Artificial Intelligence and Machine Learning Enabled Software in and as Medical devices: a systematic review. JAMA Netw Open. 2023;6(7):e2321792–2321792.

Article   Google Scholar  

Potnis KC, Ross JS, Aneja S, Gross CP, Richman IB. Artificial intelligence in breast cancer screening: evaluation of FDA device regulation and future recommendations. JAMA Intern Med. 2022;182(12):1306–12.

Siala H, Wang Y. SHIFTing artificial intelligence to be responsible in healthcare: a systematic review. Soc Sci Med. 2022;296:114782.

Yang X, Chen A, PourNejatian N, Shin HC, Smith KE, Parisien C, et al. A large language model for electronic health records. NPJ Digit Med. 2022;5(1):194.

Meskó B, Topol EJ. The imperative for regulatory oversight of large language models (or generative AI) in healthcare. NPJ Digit Med. 2023;6(1):120.

Jobin A, Ienca M, Vayena E. The global landscape of AI ethics guidelines. Nat Mach Intell. 2019;1(9):389–99.

Minssen T, Vayena E, Cohen IG. The challenges for Regulating Medical Use of ChatGPT and other large Language models. JAMA. 2023.

Ho CWL, Malpani R. Scaling up the research ethics framework for healthcare machine learning as global health ethics and governance. Am J Bioeth. 2022;22(5):36–8.

Yeung K. Recommendation of the council on artificial intelligence (OECD). Int Leg Mater. 2020;59(1):27–34.

Maddox TM, Rumsfeld JS, Payne PR. Questions for artificial intelligence in health care. JAMA. 2019;321(1):31–2.

Dzau VJ, Balatbat CA, Ellaissi WF. Revisiting academic health sciences systems a decade later: discovery to health to population to society. Lancet. 2021;398(10318):2300–4.

Ferretti A, Ienca M, Sheehan M, Blasimme A, Dove ES, Farsides B, et al. Ethics review of big data research: what should stay and what should be reformed? BMC Med Ethics. 2021;22(1):1–13.

Rahimzadeh V, Serpico K, Gelinas L. Institutional review boards need new skills to review data sharing and management plans. Nat Med. 2023;1–3.

Kling S, Singh S, Burgess TL, Nair G. The role of an ethics advisory committee in data science research in sub-saharan Africa. South Afr J Sci. 2023;119(5–6):1–3.

Google Scholar  

Cengiz N, Kabanda SM, Esterhuizen TM, Moodley K. Exploring perspectives of research ethics committee members on the governance of big data in sub-saharan Africa. South Afr J Sci. 2023;119(5–6):1–9.

Doerr M, Meeder S. Big health data research and group harm: the scope of IRB review. Ethics Hum Res. 2022;44(4):34–8.

Ballantyne A, Stewart C. Big data and public-private partnerships in healthcare and research: the application of an ethics framework for big data in health and research. Asian Bioeth Rev. 2019;11(3):315–26.

Samuel G, Chubb J, Derrick G. Boundaries between research ethics and ethical research use in artificial intelligence health research. J Empir Res Hum Res Ethics. 2021;16(3):325–37.

Murphy K, Di Ruggiero E, Upshur R, Willison DJ, Malhotra N, Cai JC, et al. Artificial intelligence for good health: a scoping review of the ethics literature. BMC Med Ethics. 2021;22(1):1–17.

Teixeira da Silva JA. Handling ethics dumping and neo-colonial research: from the laboratory to the academic literature. J Bioethical Inq. 2022;19(3):433–43.

Ferryman K. The dangers of data colonialism in precision public health. Glob Policy. 2021;12:90–2.

Couldry N, Mejias UA. Data colonialism: rethinking big data’s relation to the contemporary subject. Telev New Media. 2019;20(4):336–49.

Organization WH. Ethics and governance of artificial intelligence for health: WHO guidance. 2021.

Metcalf J, Moss E. Owning ethics: corporate logics, silicon valley, and the institutionalization of ethics. Soc Res Int Q. 2019;86(2):449–76.

Data Protection Act - OFFICE OF THE DATA PROTECTION COMMISSIONER KENYA [Internet]. 2021 [cited 2023 Sep 30]. https://www.odpc.go.ke/dpa-act/ .

Sharon T, Lucivero F. Introduction to the special theme: the expansion of the health data ecosystem–rethinking data ethics and governance. Big Data & Society. Volume 6. London, England: SAGE Publications Sage UK; 2019. p. 2053951719852969.

Reisman D, Schultz J, Crawford K, Whittaker M. Algorithmic impact assessments: a practical Framework for Public Agency. AI Now. 2018.

Morgan RK. Environmental impact assessment: the state of the art. Impact Assess Proj Apprais. 2012;30(1):5–14.

Samuel G, Richie C. Reimagining research ethics to include environmental sustainability: a principled approach, including a case study of data-driven health research. J Med Ethics. 2023;49(6):428–33.

Kwete X, Tang K, Chen L, Ren R, Chen Q, Wu Z, et al. Decolonizing global health: what should be the target of this movement and where does it lead us? Glob Health Res Policy. 2022;7(1):3.

Abimbola S, Asthana S, Montenegro C, Guinto RR, Jumbam DT, Louskieter L, et al. Addressing power asymmetries in global health: imperatives in the wake of the COVID-19 pandemic. PLoS Med. 2021;18(4):e1003604.

Benatar S. Politics, power, poverty and global health: systems and frames. Int J Health Policy Manag. 2016;5(10):599.

Download references

Acknowledgements

We would like to acknowledge the outstanding contributions of the attendees of GFBR 2022 in Cape Town, South Africa. This paper is authored by members of the GFBR 2022 Planning Committee. We would like to acknowledge additional members Tamra Lysaght, National University of Singapore, and Niresh Bhagwandin, South African Medical Research Council, for their input during the planning stages and as reviewers of the applications to attend the Forum.

This work was supported by Wellcome [222525/Z/21/Z], the US National Institutes of Health, the UK Medical Research Council (part of UK Research and Innovation), and the South African Medical Research Council through funding to the Global Forum on Bioethics in Research.

Author information

Authors and affiliations.

Department of Physical Therapy, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada

Berman Institute of Bioethics, Johns Hopkins University, Baltimore, MD, USA

Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA

Department of Philosophy and Classics, University of Ghana, Legon-Accra, Ghana

Caesar A. Atuire

Centre for Tropical Medicine and Global Health, Nuffield Department of Medicine, University of Oxford, Oxford, UK

Mahidol Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand

Phaik Yeong Cheah

Berkman Klein Center, Harvard University, Bogotá, Colombia

Armando Guio Español

Department of Radiology and Informatics, Emory University School of Medicine, Atlanta, GA, USA

Judy Wawira Gichoya

Health Ethics & Governance Unit, Research for Health Department, Science Division, World Health Organization, Geneva, Switzerland

Adrienne Hunt & Katherine Littler

African Center of Excellence in Bioinformatics and Data Intensive Science, Infectious Diseases Institute, Makerere University, Kampala, Uganda

Daudi Jjingo

ISI Foundation, Turin, Italy

Daniela Paolotti

Department of Health Sciences and Technology, ETH Zurich, Zürich, Switzerland

Effy Vayena

Joint Centre for Bioethics, Dalla Lana School of Public Health, University of Toronto, Toronto, Canada

You can also search for this author in PubMed   Google Scholar

Contributions

JS led the writing, contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. JA contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. CA contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. PYC contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. AE contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. JWG contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. AH contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. DJ contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. KL contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. DP contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper. EV contributed to conceptualization and analysis, critically reviewed and provided feedback on drafts of this paper, and provided final approval of the paper.

Corresponding author

Correspondence to James Shaw .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Shaw, J., Ali, J., Atuire, C.A. et al. Research ethics and artificial intelligence for global health: perspectives from the global forum on bioethics in research. BMC Med Ethics 25 , 46 (2024). https://doi.org/10.1186/s12910-024-01044-w

Download citation

Received : 31 October 2023

Accepted : 01 April 2024

Published : 18 April 2024

DOI : https://doi.org/10.1186/s12910-024-01044-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence
• Machine learning
• Research ethics
• Global health

BMC Medical Ethics

ISSN: 1472-6939

• General enquiries: [email protected]

Help | Advanced Search

Computer Science > Machine Learning

Title: mer 2024: semi-supervised learning, noise robustness, and open-vocabulary multimodal emotion recognition.

Abstract: Multimodal emotion recognition is an important research topic in artificial intelligence. Over the past few decades, researchers have made remarkable progress by increasing dataset size and building more effective architectures. However, due to various reasons (such as complex environments and inaccurate labels), current systems still cannot meet the demands of practical applications. Therefore, we plan to organize a series of challenges around emotion recognition to further promote the development of this field. Last year, we launched MER2023, focusing on three topics: multi-label learning, noise robustness, and semi-supervised learning. This year, we continue to organize MER2024. In addition to expanding the dataset size, we introduce a new track around open-vocabulary emotion recognition. The main consideration for this track is that existing datasets often fix the label space and use majority voting to enhance annotator consistency, but this process may limit the model's ability to describe subtle emotions. In this track, we encourage participants to generate any number of labels in any category, aiming to describe the emotional state as accurately as possible. Our baseline is based on MERTools and the code is available at: this https URL .

Submission history

Access paper:.

• HTML (experimental)
• Other Formats

References & Citations

• Google Scholar
• Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

• Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

AI Assistance in Scientific Research Raises Concerns

Research indicates that generative AI is being used in scientific writing at a significant rate some of the researchers are treating it as a valid approach that can pose a threat to real research and the true nature of scholarly work.

AI’s growing influence on scientific writing

Scholars have discovered that the volume of AI-produced writing is quite substantial compared to other kinds of writing, like journals and books. Such analysis based on linguistics hints that the use of words typically associated with large language models (LLMs) like “intricate,” “pivotal,” and “meticulously” has increased substantially in the text.

The data collected by Andrew Gray from University College London reveal that after 2023, just 1% of papers in certain fields are assisted by AI. Subsequently, in April, another study from Stanford University found that the number of biased reviews falls between 6.3 and 17.5 percent based on the research subject.

Detecting AI influence

Language tests, and statistical analysis were amongst the tools used to link words or phrases to AI assistance. Despite the fact that modifying words, like ‘red’,’result’, and ‘after’ observed less variation till 2023 and then spikes in the use of some adjectives and adverbs associated with LLM-generated content begin to happen.

Precisely, the words “meticulous,” “commendable,” and “intricate” increased that much by 117%, having hit the highest rate post-2022. The Stanford study observed a Shift in Language usage in Artificial Intelligence, which indicated that AI language continues to improve in its usage in all scientific disciplines.

The research also disclosed that AI linguistic discrimination is consistent with the disciplinary disparities in AI adoption. Fields like computer science and electrical engineering are in the teaching front of AI charter language. However, fields such as mathematics, physics, or Nature didn’t feature more dramatic shifts but rather more conservative raises.

Ethical challenges in AI-assisted academic writing

The authors, being more prolific in preprints, working in the research areas where the competition is high, and whetting an appetite for short papers, were shown to be more prone to AI-assisted writing. It is evident that this pattern throws light on the presumed relationship between time limitation and the increased amount of published content as the result of AI-generated content.

AI has been a key facilitator in speeding up research processes. However, it still raises issues of ethics when the technology is used in diverse tasks such as abstracts and other sections of scientific papers. Certain publishers consider it plagiarism, and to some extent unethical, if employed agents of LLMs discuss a scientific paper in which they are not the sole human authors.

The necessary nature of avoiding inaccuracies in AI-generated text, such as imagined quotations and examples, is yet a key feature of scholars’ communication, one should not fail to be transparent and honest. Authors who employ LLM-driven material are required to let the readers know about the research method they used to maintain research integrity and standard acts.

With AI’s increasing influence in academic writing, the architects of the academic community are confronted with the serious challenge of solving ethical implications and ensuring the reliability of research articles. AI is a great technology that significantly facilitates research activities, but honesty and integrity still ought to be maintained in order to preserve scientific integrity.