mlsanityData to 14 Oct 2026

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

arXiv 2407.20371 ↗First posted 29 Jul 2024cs.CY cs.AI cs.CLcited by 51

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence (AI) hiring tools have revolutionized resume screening, and large language models (LLMs) have the potential to do the same. However, given the biases which are embedded within LLMs, it is unclear whether they can be used in this scenario without disadvantaging groups based on their protected attributes. In this work, we investigate the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection. Using that framework, we then perform a resume audit study to determine whether a selection of Massive Text Embedding (MTE) models are biased in resume screening scenarios. We simulate this for nine occupations, using a collection of over 500 publicly available resumes and 500 job descriptions. We find that the MTEs are biased, significantly favoring White-associated names in 85.1% of cases and female-associated names in only 11.1% of cases, with a minority of cases showing no statistically significant differences. Further analyses show that Black males are disadvantaged in up to 100% of cases, replicating real-world patterns of bias in employment settings, and validate three hypotheses of intersectionality. We also find an impact of document length as well as the corpus frequency of names in the selection of resumes. These findings have implications for widely used AI tools that are automating employment, fairness, and tech policy.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). Builds on 15 of its 53 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

15 of 53 references.

References · 15

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  3. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 483
  4. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  5. 2020Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biasescited by 167
  6. 2024Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokenscited by 153
  7. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  8. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 98
  9. 2023ROBBIE: Robust Bias Evaluation of Large Generative Language Modelscited by 53
  10. 2023The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactionscited by 45
  11. 2021Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Modelscited by 39
  12. 2022American == White in Multimodal Language-and-Image AIcited by 39
3 more
  1. 2023'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusioncited by 33
  2. 2023Towards a Holistic Approach: Understanding Sociodemographic Biases in NLP Models using an Interdisciplinary Lenscited by 9
  3. 2021Degendering Resumes for Fair Algorithmic Resume Screeningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 25; 2026: 22.

51 papers.

Sort:

By area:

  1. 2025Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?cited by 51
  2. 2025Correlated Errors in Large Language Modelscited by 45
  3. 2025AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screeningcited by 20
  4. 2025Explainability in Practice: A Survey of Explainable NLP Across Various Domainscited by 11
  5. 2025The Bias is in the Details: An Assessment of Cognitive Bias in LLMscited by 10
  6. 2025No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomycited by 8
  7. 2024Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensivenesscited by 7
  8. 2025Evaluating the Promise and Pitfalls of LLMs in Hiring Decisionscited by 7
  9. 2025Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoderscited by 6
  10. 2025Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Modelscited by 6
  11. 2024Towards Effective Discrimination Testing for Generative AIcited by 5
  12. 2025Fragile Preferences: A Deep Dive Into Order Effects in Large Language Modelscited by 5
38 more
  1. 2025On the Mutual Influence of Gender and Occupation in LLM Representationscited by 4
  2. 2025Gender and Positional Biases in LLM-Based Hiring Decisions: Evidence from Comparative CV/R'esum'e Evaluationscited by 4
  3. 2025Model Misalignment and Language Change: Traces of AI-Associated Language in Unscripted Spoken Englishcited by 4
  4. 2024Learning With Multi-Group Guarantees For Clusterable Subpopulationscited by 3
  5. 2025HInter: Exposing Hidden Intersectional Bias in Large Language Modelscited by 3
  6. 2025The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selectioncited by 3
  7. 2025Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolutioncited by 3
  8. 2025Talent or Luck? Evaluating Attribution Bias in Large Language Modelscited by 2
  9. 2026PJB: A Reasoning-Aware Benchmark for Person-Job Retrievalcited by 2
  10. 2026Locating and Controlling Implicit Personalization in Large Language Modelscited by 2
  11. 2024Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Reviewcited by 1
  12. 2025Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contextscited by 1
  13. 2025Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology coursecited by 1
  14. 2025GenderBench: Evaluation Suite for Gender Biases in LLMscited by 1
  15. 2025JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inferencecited by 1
  16. 2025Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMscited by 1
  17. 2025From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitmentcited by 1
  18. 2026Identity-Robust Language Model Generation via Content Integrity Preservationcited by 1
  19. 2026Making AI Evaluation Deployment Relevant Through Context Specificationcited by 1
  20. 2026PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Datasetcited by 1
  21. 2026Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curationcited by 1
  22. 2026Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiringcited by 1
  23. 2026Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflowscited by 1
  24. 2025Fairness Is Not Enough: Auditing Competence and Intersectional Bias in AI-powered Resume Screeningcited by 0
  25. 2025How Large Language Models Systematically Misrepresent American Climate Opinionscited by 0
  26. 2026BiasLab: A Multilingual Dual-Framing Framework for LLM Bias Measurement, Applied to Workplace and HR Contextscited by 0
  27. 2026Rank-Constrained Adaptation for Reliable Real-World Performancecited by 0
  28. 2026A Representation-Level Assessment of Bias Mitigation in Foundation Modelscited by 0
  29. 2026Why AI Harms Can't Be Fixed One Identity at a Time: What 5300 Incident Reports Reveal About Intersectionalitycited by 0
  30. 2026Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Auditcited by 0
  31. 2026The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Datacited by 0
  32. 2026Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflowscited by 0
  33. 2026Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Levelcited by 0
  34. 2026Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMscited by 0
  35. 2026Counterfactual Bias Testing for Application Tracking Systemcited by 0
  36. 2026Beyond the Name: Demographic Leakage in De-Identified R'esum'es and Evaluation Artifacts in LLM Bias Auditscited by 0
  37. 2026Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitmentcited by 0
  38. 2026White Men Without Degrees Receive the Lowest Ratings from Large Language Modelscited by 0

50 most cited of 51 All 51 (JSON)