Auditing large language models for race & gender disparities: Implications for artificial intelligence-based hiring
Open accessAbstract
Rapid advances in artificial intelligence (AI), including large language models (LLMs) with abilities that rival those of human experts on a wide array of tasks, are reshaping how people make important decisions. At the same time, critics worry that LLMs may inadvertently discriminate against some groups. To address these concerns, recent regulations call for auditing the LLMs used in important decisions such as hiring. But neither current regulations nor the scientific literature offers clear guidance on how to conduct these audits. In this article, we propose and investigate one approach for auditing algorithms: correspondence experiments , a widely applied tool for detecting bias in human judgments. We applied this method to a range of LLMs instructed to rate job candidates using a novel data set of job applications for K-12 teaching positions in a large American public school district. By altering the application materials to imply that candidates are members of specific demographic groups, we measured the extent to which race and gender influenced the LLMs’ ratings of the candidates’ suitability. We found moderate race and gender disparities, with the models slightly favoring women and non-White candidates. This pattern persisted across several variations in our experiment. It is unclear what might be driving these disparities, but we hypothesize that they stem from posttraining efforts, which are part of the LLM training process and intended to correct biases in these m…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Gaebler et al. found that across 11 LLMs, race- and gender-based score differences from name manipulation were statistically significant but modest in absolute magnitude.
“Gaebler et al. [32] similarly found that across 11 LLMs, race- and gender-based score differences from name manipulation were statistically significant but modest in absolute magnitude.”
From All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs? (2026) · cites this paper as [32]
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · see citing works
Statistics and Causal Inference
Holland, P. W. (1986) · Journal of the American Statistical Association · doi:10.1080/01621459.1986.10478354 · Cited by 5,293 · see citing works
Bertrand, M., & Mullainathan, S. (2004) · American Economic Review · doi:10.1257/0002828042002561 · Cited by 4,504 · see citing works
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501 · see citing works
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · see citing works
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · see citing works
Artificial Intelligence in Human Resources Management: Challenges and a Path Forward
Tambe, P., Cappelli, P., & Yakubovich, V. (2019) · California Management Review · doi:10.1177/0008125619867910 · Cited by 1,609 · see citing works
Self-citationAlgorithmic Decision Making and the Cost of Fairness
Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., & Huq, A. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098095 · Cited by 1,149 · see citing works
Self-citationFairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988 · see citing works
Inherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943 · see citing works
Mitigating bias in algorithmic hiring: evaluating claims and practices
Raghavan, M., Barocas, S., Kleinberg, J., & Levy, K. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372828 · Cited by 845 · see citing works
Zafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · see citing works
Sweeney, L. (2013) · Queue · doi:10.1145/2460276.2460278 · Cited by 477 · see citing works
Whitened Résumés: Race and Self-Presentation in the Labor Market
Kang, S. K., DeCelles, K. A., Tilcsik, A., & Jun, S. (2016) · Administrative Science Quarterly · doi:10.1177/0001839216639577 · Cited by 441 · see citing works
Race as a Bundle of Sticks: Designs that Estimate Effects of Seemingly Immutable Characteristics
Sen, M., & Wasow, O. (2016) · Annual Review of Political Science · doi:10.1146/annurev-polisci-032015-010015 · Cited by 422 · see citing works
A snapshot of the frontiers of fairness in machine learning
Chouldechova, A., & Roth, A. (2020) · Communications of the ACM · doi:10.1145/3376898 · Cited by 362 · see citing works
Avoiding Discrimination through Causal Reasoning
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Schölkopf, B. (2017) · arXiv · doi:10.48550/arxiv.1706.02744 · Cited by 358 · see citing works
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340 · see citing works
Auditing Algorithms: Understanding Algorithmic Systems from the Outside In
Metaxa, D., Park, J., Robertson, R. E., Karahalios, K., Wilson, C., Hancock, J., & Sandvig, C. (2021) · Found. Trends Hum. Comput. Interact. · doi:10.1561/1100000083 · Cited by 218 · see citing works
Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits
Bandy, J. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449148 · Cited by 193 · see citing works
Causal Effects of Perceived Immutable Characteristics
Greiner, D., & Rubin, D. (2011) · Review of Economics and Statistics · doi:10.1162/rest_a_00110 · Cited by 143 · see citing works
Jiang, A. Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., Chaplot, D. S., Casas, D. D. L., Hanna, E. B., Bressand, F., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.04088 · Cited by 143 · see citing works
Ayres, I., Banaji, M. R., & Jolls, C. (2015) · The RAND Journal of Economics · doi:10.1111/1756-2171.12115 · Cited by 119 · see citing works
Causal Reasoning for Algorithmic FairnessPreprint
Loftus, J. R., Russell, C., Kusner, M. J., & Silva, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.05859 · Cited by 110 · see citing works
Measuring Racial Discrimination in American Housing Markets: The Housing Market Practices Survey.
Wienk, R. E. (1979) · Cited by 107 · see citing works
Counterfactual risk assessments, evaluation, and fairness
Coston, A., Mishler, A., Kennedy, E. H., & Chouldechova, A. (2020) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3351095.3372851 · Cited by 90 · see citing works
What's sex got to do with machine learning?
Hu, L., & Kohler-Hausmann, I. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3375674 · Cited by 74 · see citing works
Auditing Work: Exploring the New York City algorithmic bias audit regime
Groves, L., Metcalf, J., Kennedy, A., Vecchione, B., & Strait, A. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658959 · Cited by 59 · see citing works
The Silicon Ceiling: Auditing GPT’s Race and Gender Biases in Hiring
Armstrong, L., Liu, A., MacNeil, S., & Metaxa, D. (2024) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3689904.3694699 · Cited by 59 · see citing works
Computer says ‘no’: Exploring systemic bias in ChatGPT using an audit approach
Lippens, L. (2024) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2024.100054 · Cited by 55 · see citing works
Gaddis, S. M. (2019) · Sociology of Race and Ethnicity · doi:10.1177/2332649219870183 · Cited by 55 · see citing works
Gaddis, S. M., & Ghoshal, R. (2019) · Socius Sociological Research for a Dynamic World · doi:10.1177/2378023120972287 · Cited by 51 · see citing works
Veldanda, A., Grob, F., Thakur, S., Pearce, H., Tan, B., Karri, R., & Garg, S. (2023) · arXiv.org · doi:10.48550/arxiv.2310.05135 · Cited by 42 · see citing works
A Causal Framework for Observational Studies of Discrimination
Gaebler, J., Cai, W., Basse, G., Shroff, R., Goel, S., & Hill, J. (2022) · Statistics and Public Policy · doi:10.1080/2330443x.2021.2024778 · Cited by 28 · see citing works
Self-citationRace influences professional investors’ financial judgments
Lyons-Padilla, S., Markus, H. R., Monk, A., Radhakrishna, S., Shah, R., Dodson, N. A. “., & Eberhardt, J. L. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1822052116 · Cited by 27 · see citing works
Blind Justice: Algorithmically Masking Race in Charging Decisions
Chohlas-Wood, A., Nudell, J., Yao, K., Lin, Z. J., Nyarko, J., & Goel, S. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462524 · Cited by 26 · see citing works
Self-citationPrincipal Fairness for Human and Algorithmic Decision-Making
Imai, K., & Jiang, Z. (2023) · Statistical Science · doi:10.1214/22-sts872 · Cited by 20 · see citing works
Nabi, R., & Shpitser, I. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11553 · Cited by 20 · see citing works
Mitigating Included- and Omitted-Variable Bias in Estimates of Disparate ImpactPreprint
Jung, J., Corbett‐Davies, S., Gaebler, J., Shroff, R., & Goel, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.05651 · Cited by 16 · see citing works
Self-citationPath-Specific Counterfactual Fairness
Chiappa, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017801 · Cited by 16 · see citing works
Evaluating and Mitigating Discrimination in Language Model Decisions
Tamkin, A., Askell, A., Lovitt, L., Durmus, E., Joseph, N., Kravec, S., Nguyen, K., Kaplan, J., & Ganguli, D. (2023) · arXiv · doi:10.48550/arxiv.2312.03689 · Cited by 11 · see citing works
Equal Opportunity and Affirmative Action via Counterfactual PredictionsPreprint
Wang, Z., Sridhar, D., & Blei, D. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10870 · Cited by 10 · see citing works
What Should We Do when Our Ideas of Fairness Conflict?
Raghavan, M. (2023) · Communications of the ACM · doi:10.1145/3587930 · Cited by 8 · see citing works
What's in a Name? Auditing Large Language Models for Race and Gender BiasPreprint
Salinas, A., Haim, A., & Nyarko, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.14875 · Cited by 8 · see citing works
Nghiem, H. T., Prindle, J., Zhao, J., & Daumé, H. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.413 · Cited by 8 · see citing works
Measuring Gender and Racial Biases in Large Language ModelsPreprint
An, J., Huang, D., Lin, C., & Tai, M. (2024) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2403.15281 · Cited by 5 · see citing works
First-Person Fairness in ChatbotsPreprint
Eloundou, T., Beutel, A., Robinson, D. G., Gu-Lemberg, K., Brakman, A.-L., Mishkin, P., Shah, M., Heidecke, J., Weng, L., & Kalai, A. T. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.19803 · Cited by 4 · see citing works
Lippens, L., Vermeiren, S., & Baert, S. (2023) · European Economic Review · doi:10.1016/j.euroecorev.2022.104315
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
Flagged first, then by citations
Cited by
Sorted by citations
Hsieh, C., Wang, D., He, Y., & Hsieh, D. W. (2026) · Review of Public Personnel Administration · doi:10.1177/0734371x261417717 · Cited by 2 · see citing works
Bilon, X. J. (2025) · Journal of Decision System · doi:10.1080/12460125.2025.2599912 · Cited by 1 · see citing works
Distinguishing Task-Specific and General-Purpose AI in Regulation
Wang, J., Selbst, A. D., Barocas, S., & Venkatasubramanian, S. (2026) · ACM Symposium on Computer Science and Law (CSLAW) · doi:10.1145/3788646.3789523 · Cited by 3 · see citing works
All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs?
Kim, S., Janssen, M. A., Wang, J., Min-Venditti, A., Karanjia, N., & Anderies, J. M. (2026) · arXiv · doi:10.48550/arxiv.2604.17247
Wijethunga, W. M. S., & Wijesuriya, W. M. R. M. (2025) · International Conference on Information Technology Research (ICITR) · doi:10.1109/icitr69413.2025.11353547
The Ethics of Predictive Analytics in Employment and Hiring Practice
Dordunoo, L. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-1016-7.ch001
Unveiling Nuance: Understanding Young Adults’ Enactment of Sexual Agency
Cooper, S. C., Memaj, I., Porter, A. N., Abdelfadeel, E., Yepes, C., Muther, P., & Calderon, J. (2026) · Sexuality & Culture · doi:10.1007/s12119-026-10552-3
Comparative AI ‐Based Framework for Name‐Based Demographic Inference in the Indian Subcontinent
Sultana, S., Atib, Z. B. M., Redoy, M. O. F., Rahman, M. A., Uddin, M. S., & Habib, M. T. (2026) · Engineering Reports · doi:10.1002/eng2.70902
Grenzebach, J., & Radüntz, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29596-5_7
Measuring disparate impact in human and machine decisions
Jung, J., Corbett‐Davies, S., Gaebler, J., Shroff, R., & Goel, S. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2509765122
Self-citationNot for people like me: How frontier AI models redirect skeptical rural school staff
Rossmiller, Z. (2026) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2026.100659
Iancu, C. L., Oprea, S., Bârã, A., & Iordache, D.-M. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01108-4
From the platform society to the AI society
Törnberg, P., & Uitermark, J. (2026) · Dialogues on Digital Society · doi:10.1177/29768640261487931
Measuring Position Bias in LLM-as-a-Judge for Hiring
Aminou, L., Daaif, A., Soulami, M., & Youssfi, M. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11699959
How Stable Are Ethical Choices in Large Language Models? Evidence from Trolley-Style DilemmasPreprint
Nguyen, H. T., Goebel, R. G., Stathis, K., Toni, F., Satoh, K., Zin, M. M., Fungwacharakorn, W., & Kong, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7619818
Baig, M. S. A., & Gillani, S. A. (2026) · Journal of Business Venturing Insights · doi:10.1016/j.jbvi.2026.e00682
- Authors
- Gaebler, J. D., Goel, S., Huq, A., & Tambe, P.
- Affiliations
- Harvard University (US)
- University of Chicago (US)
- University of Pennsylvania (US)
- Corresponding author
- Gaebler, Johann D.
- Venue
- Behavioral Science & Policy
- Publisher
- SAGE Publications
- Published
- 2024-10
- Volume
- 10
- Issue
- 2
- Pages
- 46-55
- ISSN
- 2379-4607 (ISSN-L)
- 2379-4615
- OpenAlex
- W4408342414
- Cited by
- 15
- References
- 49
- Citations by year
- 2026: 13 · 2025: 2
- FWCI
- 6.20
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Behavioral Science & Policy (publishedVersion, cc-by-nc)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Sociology and Political Science › Names, Identity, and Discrimination Research
- Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › AI and HR Technologies
- Keywords
- large language models, algorithmic auditing, algorithmic discrimination, racial disparities, gender disparities, correspondence experiment, algorithmic accountability
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
