Can Generative AI Improve Social Science?
Open accessThe DOI matches its Crossref record; 98 of the 98 references it cites were found in a registry or an index.
Abstract
Artificial intelligence that can produce realistic text,images, and other human-like outputs is currently transforming many different industries. Yet it is not yet known how such tools might transform social science research. In the first section of this article, I assess the potential of Generative AI to improve online experiments, agent-based models, and automated content analyses.I also discuss whether these tools may help social scientists perform literature reviews, identify novel research questions, and develop hypotheses to explain them. Next, I evaluate whether Generative AI can help social scientists with more mundane tasks such as acquiring advancedprogramming skills or writing more effective prose. In the second section of this article I discuss the limitations of Generative AI as well as how these tools might be employed by researchers in an ethical manner. I discuss how bias in the processes and data used to train these tools can negatively impact social science research as well as a rangeof other challenges related to accuracy, reproducibility,interpretability, and efficiency. I conclude by highlighting the need for increased collaboration between social scientists and artificial intelligence researchers--- not only to ensure that such tools are used in a safe and ethical manner, but also because the progress of artificial intelligence may require deeper understanding of theories of human behavior
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Research assistant: Beyond their application in specialized domains, LLM-based agents are increasingly adopted as versatile assistants in the broad field of social science research [105,114].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [114]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
Agendas and instability in American politics
(1993) · Choice Reviews Online · doi:10.5860/choice.31-0574 · Cited by 5,981
Experimental evidence of massive-scale emotional contagion through social networks
Kramer, A. D. I., Guillory, J. E., & Hancock, J. T. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1320040111 · Cited by 3,687
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684
(2018) · Cited by 3,510
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Vinyals, O., Babuschkin, I., Czarnecki, W. M., Mathieu, M., Dudzik, A., Chung, J., Choi, D. H., Powell, R., Ewalds, T., Georgiev, P., et al. (2019) · Nature · doi:10.1038/s41586-019-1724-z · Cited by 3,455
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Growing Artificial Societies: Social Science from the Bottom Up
Epstein, J. M., & Axtell, R. L. (1996) · doi:10.7551/mitpress/3374.001.0001 · Cited by 2,441
Research works printed but not linked: 3
- [15]15. Daneshjou, Roxana et al. 2021. "Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review." JAMA Dermatology 157(11): 1362-69.
- [39]39. Princeton, N.J.: Princeton University Press.
- [48]48. Yang, Kai-Cheng, and Filippo Menczer. 2023. "Large Language Models Can Rate News Outlet Credibility." http://arxiv.org/abs/2304.00228 (April 25, 2023). · arXiv
Cited by
Items 501–600 of 704
Navigating digital norms: Enforcement mechanisms and user adaptation strategies in online forums
Kenntemich, C. (2025) · Publication Server of Kaiserslautern University of Technology (Kaiserslautern University of Technology) · doi:10.26204/kluedo/8812
Measurement of LLM's Philosophies of Human NaturePreprint
Ni, M., Wu, E., 東, 公., Yang, Z., Li, L., Lin, C.-C., Lin, K., Wang, L., & Zuo, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.02304
A novel, human-in-the-loop computational grounded theory framework for big social data
Alqazlan, L. (2024) · Warwick Research Archive Portal (University of Warwick)
Generador de datos sintéticos tabulares basado en modelos de difusión
Arroni del Riego, S. (2024) · Archivo Digital UPM (Universidad Politécnica de Madrid)
Experiencia de uso de Chat GPT-3 como asistente de búsqueda en revisiones sistemáticas de literatura
Borges, C. C. (2025) · Revista latinoamericana de metodología de la investigación social
Social Biases in Generative AI: Implications for Bias Mitigation in Decision Making
Gurkan, N., & Njoki, K. (2025) · AIS Electronic Library (AISeL)
Instruction-based fine-tuning of open-source llms forpredictıng customer purchase behaviors
Ergül, H. İ. (2024) · Sabanci University
Three Essays in Asset Pricing and Machine Learning
Bini, P. (2025) · eCommons (Cornell University) · doi:10.7298/v9z1-xj33
LLM Survey Framework: Coverage, Consistency, IdentificationPreprint
Wu, J. C., Xi, J., & Xie, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5517960
Big Data and Machine Learning Methods
Mützel, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-25143-6_56-1
Meng, Y., Ye, L., He, E., Yan, Z., Liu, Z., Yu, Y., Guan, Y., & Ding, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.23188
Abramson, C. M. (2025) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/2s8fy_v1
Zamojska, M., & Chudziak, J. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.17060
حميده, أ. ع. ع. (2025) · Journal of Arts, Literature, Humanities and Social Sciences · doi:10.33193/jalhss.127.2025.1593
Psychometric Comparability of LLM-Based Digital TwinsPreprint
Zhang, Y., & Ma, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.5967255
The Qualitative Laboratory: Theory Prototyping and Hypothesis Generation with Large Language ModelsPreprint
Draelants, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.00797
Generative AI in Immersive Museums: Quantitative Evaluation of Artistry and Visitor Experience
Shu, X., & Yang, S. (2025) · International Conference on Computer Technology, Digital Media and Communication · doi:10.1145/3783669.3783678
Kahenya, N. P. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-8795-6.ch010
Navigating the World of Digital Data: The Challenges of Social Research Methods
Catone, M. C. (2026) · Routledge eBooks · doi:10.4324/9781003671954
Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?Preprint
Gusella, F., & Vicario, E. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6066372
ARTIFICIAL INTELLIGENCE AND ITS ROLE IN THE DEVELOPMENT OF SOCIAL SCIENCES AND HUMANITIES
Orbik, Z. (2025) · Scientific Papers of Silesian University of Technology Organization and Management Series · doi:10.29119/1641-3466.2025.233.24
Seibt, J., & Hakli, R. (2026) · The MIT Press eBooks · doi:10.7551/mitpress/10777.003.0004
Psychometric Comparability of LLM-Based Digital TwinsPreprint
Zhang, Y., & Ma, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.14264
Surveying with AI: Simulating Human Responses Using Personalized LLM Agents and Social Media Data
Liang, S., Ren, H., Zhang, T., Liu, X., Yin, Z., & Hu, D. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343347
Lyu, Z., Takikawa, H., & Shimokubo, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5512197
Syme, K., Motos, N., & Placek, C. D. (2026) · Royal Society Open Science · doi:10.1098/rsos.251766
Yue, H., Di, Z., Jiang, M., Li, B., Hao, H., Song, Y., Jiang, B., & Zhou, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.15034
Fang, Y., & Zhou, T. (2026) · Information & Management · doi:10.1016/j.im.2026.104322
Dixon, J. C., & Buchmann, H. (2026) · Teaching Sociology · doi:10.1177/0092055x261422474
Schück, F. (2026) · Frontiers in Water · doi:10.3389/frwa.2026.1749745
Reimagining Education with Generative Artificial Intelligence
KAYA, M. M., & Polat, H. (2024) · Ataturk University - AVESIS
Advanced Statistics for Psychology: A practical handbook for fundamentals and application
(2026) · Fondazione Bologna University Press eBooks · doi:10.30682/9791254777558
About Cooperative Behavior of LLM Agents in Different Repeated Social Dilemma Game Contexts
Yılmaz, H., & Kılıç, H. (2026) · International Informatics and Software Engineering Conference (IISEC) · doi:10.1109/iisec69317.2026.11418487
Agentic Framework for Political Biography ExtractionPreprint
Zhu, Y., Yang, S., Zhu, J., & Jiang, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.18010
Ishii, K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7144-4_30
From Tokens To Agents: A Researcher's Guide To Understanding Large Language ModelsPreprint
Barolo, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.19269
Ahmed, M. M., Kousar, F., Khanum, B. H., J, B. C., M, M. G., & Durrani, O. K. (2025) · IEEE Global Conference on Wireless Computing and Networking (GCWCN) · doi:10.1109/gcwcn66157.2025.11448423
Deep Research on a Loop: Using AI Agents to Construct Economic DatasetsPreprint
Galiani, S., Afonso, S., Gálvez, R. H., & Sosa, R. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6502499
Are Transition and Physical Climate Risks Priced? Evidence from Directional News-Based MeasuresPreprint
Toussaint, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6431199
Belief Explorer: A Preliminary Evaluation of AI-Mediated Socratic Dialogue for Epistemic Reflection
Delaflor, M., Solorzano, C. D., & Toxtli, C. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799391
Li, Y., Lu, H., & Yu, C. (2026) · Information Communication & Society · doi:10.1080/1369118x.2026.2659280
The Role of Habit in Promoting Generative AI Adoption Among Social Science Students and Researchers
Spilbergs, A. (2026) · International Journal of Education and Information Technologies · doi:10.46300/9109.2026.20.8
Artificial Intelligence and Computation in the Social Sciences: A Paradigm Shift
Boyd, R. L., Srinivas, S., Phadke, S., Wilson, S. R., & Pasca, P. (2026) · Oxford University Press eBooks · doi:10.1093/9780197807309.003.0003
Yeboah, R., Adu, D. A., Ntim, C. G., Morrison, E. A., & Saa, V. Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6626983
Raju, S. D. (2025) · Tampere University Institutional Repository (Tampere University)
Kambeitz, J. P. (2026) · Research Square · doi:10.21203/rs.3.rs-9291631/v1
Lanzeni, D., & Korsmeyer, H. (2026) · Qualitative Inquiry · doi:10.1177/10778004261440831
Méthodologies innovantes en recherche marketing : vers une approche comparative par triangulation
ECH-CHATI, A., Ouiddad, S., & Nadi, M. (2026) · African Scientific Journal · doi:10.5281/zenodo.19921936
BenCSSmark: Making the Social Sciences Count in LLM Research
Chatelain, A., Ollion, É., Guan, Q., Fabre, D., Goeuriot, L., Chapuis, É., Beloued, A., Candito, M., Hervé, N., & Schwab, D. (2026) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/3cd2b8m83z28
Xiong, J. (2026) · AI & Innovation · doi:10.1002/aiv2.70003
BenCSSmark: Making the Social Sciences Count in LLM ResearchPreprint
Chatelain, A., Ollion, É., Guan, Q., Fabre, D., Goeuriot, L., Chapuis, É., Beloued, A., Candito, M., Hervé, N., & Schwab, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.04886
Information Aggregation with AI AgentsPreprint
Galanis, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6479841
Dai, A. X. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2667475
Assessing and Mitigating Miscalibration in LLM-Based Social Science MeasurementPreprint
Wang, H., Deng, N., & Yang, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.11954
Agentic AI for Data Discovery in the Social Sciences and Humanities
Routsis, V., Gan, Y., Uprety, S., & Bikakis, A. (2026) · Routledge eBooks · doi:10.4324/9781003666530-3
Yunus, M. A., & Soner, A. K. I. N. (2026) · Pamukkale University Journal of Social Sciences Institute · doi:10.30794/pausbed.1794628
The Impact of Heatwaves on Population Health: A Large Language Model-Enhanced Agent-Based SimulationPreprint
Liu, Y., Liu, Y., Lu, T., Zhang, H., Wang, Z., & Dai, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.15918
Societal Risks of Generative AI: A Comparative Analysis
Mevada, J. R., Deshmukh, P. D., Panchal, S. V., Lakhe, A., & Vaishnav, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-19684-2_37
Rollin, P., & Levints, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-26629-4.00322-1
Sociology beyond computation? Alternative ways of researching digital life
Ivana, G. (2026) · Acta Sociologica · doi:10.1177/00016993261453267
García, E. D. H., Jiménez, P. D. L. J., Capuñay, J. E. C., Maldonado, H. I., Quispe, Y. C., Flores, G. V. G., Cabrera, A. D. M., Sanchez, R. F. A., Sánchez, E. Q., & Ussa-Lopez, Y. E. (2026) · doi:10.48209/978-65-5417-731-3
AI Contagion in Social NetworksPreprint
Bos, O., & Stefano Bosi, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.15206
Huang, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.18264
AI Contagion in Social NetworksPreprint
Bos, O., & Stefano Bosi, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6901119
Chen, J.-H., & Lu, H.-C. (2026) · Journal of Homosexuality · doi:10.1080/00918369.2026.2690193
AI as “Artificial Immigrants”? A Content Analysis of the U.S. News Media Framing of AI Threats
Pan, Y., Herrera, S., & Wang, Y. (2026) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2026.2692543
The changing relationship between new cleavages and policy outcomes
Prosser, T., & Dolinsky, A. O. (2026) · Parliamentary Affairs · doi:10.1093/pa/gsag026
Fooladi, M., & Bottino, F. (2026) · arXiv (Cornell University) · doi:10.63317/2wbwmwq3jwfg
Thinking With a Machine: An AI Agent’s Account of Agentic Research in Clinical Psychology
Refoua, E., & Bar, M. (2026) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.18653/v1/2026.clpsych-1.29
Regulating Algorithmic Bias: Normative Challenges of AI Ethics in Automated Decision-Making
Andersson, M., Lindström, M., & Nilsson, J. (2025) · Rechtsnormen Journal of Law · doi:10.70177/rjl.v3i3.2214
Yu, Q., Webb, J., Hunte, R., & Arachchilage, C. D. P. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-18849-6_17
Are LLMs Good for Synthetic Data? A Systematic Synthetic Dataset Validation
Akinifev, I. A., & Bodrunova, S. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31407-9_15
Jia, C., Huang, S., Xu, Z., Wang, J., Li, T., & Xiao, Y. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105039
Beyond words: How LLMs mirror human needs and values generating synthetic data
Chulvi, B., Gonzalez, J. Á., Fontanella, L., & Rangel, F. (2026) · Big Data & Society · doi:10.1177/20539517261457421
LLMs for Qualitative and Mixed-Methods Social Network AnalysisPreprint
Boudourides, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.14045
Chanut-Guieu, C., & Guieu, G. (2026) · Revue internationale P M E Économie et gestion de la petite et moyenne entreprise · doi:10.7202/1126465ar
Wei, X., Chen, Z., Yu, J., & Du, Y. (2026) · International Public Management Journal · doi:10.1080/10967494.2026.2696851
李, 曜., & 王, 斌. (2026) · Global Journal of Media Studies · doi:10.26599/gjms.2026.9330017
The End of Theory in Social Science? AI and Sleepwalking into Epistemic SurrenderPreprint
Smith, A. N., & Humphries, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6807338
Rubenstein, E. P. (2026) · Advanced International Journal of Multidisciplinary Research · doi:10.62127/aijmr.2026.v04i04.1425
What kind of field is computational social science? Fragmentation, pluralism, and unification
Ginnerskov, J. (2026) · Theory and Society · doi:10.1007/s11186-026-09732-9
LLMs for Qualitative and Mixed-Methods Social Network AnalysisPreprint
Boudourides, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7123398
Nudging Sustainable Choices through LLM-Generated Recommendation ExplanationsPreprint
Halimeh, H., Jannach, D., & Müller, O. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.25726
Generative AI in ELT Graduate-Level Research Education: An Integrative Review
Altunay, O., & Topkaya, E. Z. (2026) · DergiPark
Explanatory and Causal Methodology in Sociology: Developments and Current Issues
Sonntag, N., Otte, G., Leitgöb, H., Nisic, N., & Raub, W. (2026) · KZfSS Kölner Zeitschrift für Soziologie und Sozialpsychologie · doi:10.1007/s11577-026-01091-8
Wu, Z., Luo, Y., Zhang, P., Yang, C., & Zhang, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.28439
Cho, E. H., & Lee, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7212319
Big Data and Machine Learning Methods
Mützel, S. (2026) · Springer eBooks · doi:10.1007/978-3-032-11405-1_56
Lan, S., Zhang, X., & Wang, X. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-08575-0
Neuberger, F. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7171998
Randomness in Large Language Models: What Researchers Need to Know (and Report)Preprint
Coqueret, C., Llull, J., Oswald, F., Pérignon, C., Scheuch, C., & Vilhuber, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7189878
SimuGov: A Simulation Optimization Framework for Generative AI Governance Strategy Design
Zhang, B., Li, J., Tang, Q., & Zhu, F. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818903
A Sociological Eye on AI. Key Concepts, Analytical Dimensions, and Methodological Tensions
Solaroli, M., & Garzonio, E. (2026) · Sociologica · doi:10.60923/issn.1971-8853/23907
Nyyssönen, I. (2026) · Jyväskylä University Digital Archive (University of Jyväskylä)
Navigating AI disruption: Systems theory framework for the European Social Survey
Malnar, B. (2026) · Current Sociology · doi:10.1177/00113921261474537
Mahmud, H., Ullah, K. A., Khojasteh, M. J., Heard, J. R., & David, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.09717
Schneider, P. J. (2026) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-11010
Metadata
- Authors
- Bail, C. A.
- Affiliations
- Duke University (US)
- Corresponding author
- Bail, Christopher A.
- ORCID
- Bail, Christopher A.
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- Center for Open Science
- Published
- 2023-05-12
- Volume
- 121
- Issue
- 21
- Pages
- e2314021121-e2314021121
- ISSN
- 0027-8424 (ISSN-L)
- PMC
- PMC11127003
- OpenAlex
- W4396781199
- Cited by
- 369
- References
- 90
- Citations by year
- 2026: 143 · 2025: 160 · 2024: 55 · 2023: 11
- FWCI
- 148.38
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- SocArXiv (OSF Preprints) (submittedVersion, cc-by-nd)
- SocArXiv (OSF Preprints) (submittedVersion)
- Funders
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (P2CHD065563)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- generative AI, social science research, survey research, online experiments, computational text analysis, agent-based modeling, training data bias, research ethics, replication, environmental impact of AI, human behavior
- MeSH terms
- Artificial Intelligence, Humans, Social Sciences
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.