mlsanityData to 7 Oct 2026

The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring

arXiv 2405.04412 ↗First posted 7 May 2024cs.CY cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an AI audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment (Study 1) and resume generation (Study 2). In Study 1, we ask GPT to score resumes with 32 different names (4 names for each combination of the 2 gender and 4 racial groups) and two anonymous options across 10 occupations and 3 evaluation tasks (overall rating, willingness to interview, and hireability). We find that the model reflects some biases based on stereotypes. In Study 2, we prompt GPT to create resumes (10 for each name) for fictitious job candidates. When generating resumes, GPT reveals underlying biases; women's resumes had occupations with less experience, while Asian and Hispanic resumes had immigrant markers, such as non-native English and non-U.S. education and work experiences. Our findings contribute to a growing body of literature on LLM biases, particularly in workplace contexts.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 21 of its 107 references that are in the map. First posted on arXiv 7 May 2024.

Builds on

21 of 107 references.

References · 21

  1. 2021Ethical and social risks of harm from Language Modelscited by 957
  2. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  3. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  4. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  5. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  6. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  7. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 170
  8. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  9. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  10. 2013Discrimination in Online Ad Deliverycited by 93
  11. 2021Sparks: Inspiration for Science Writing using Language Modelscited by 80
  12. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
9 more
  1. 2024AI auditing: The Broken Bus on the Road to AI Accountabilitycited by 42
  2. 2019What does it mean to solve the problem of discrimination in hiring? Social, technical and legal perspectives from the UK on automated hiring systemscited by 38
  3. 2021Intersectional Bias in Causal Language Modelscited by 24
  4. 2023Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativitycited by 23
  5. 2023Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPTcited by 23
  6. 2024Auditing Work: Exploring the New York City algorithmic bias audit regimecited by 18
  7. 2021A Silicon Valley Love Triangle: Hiring Algorithms, Pseudo-Science, and the Quest for Auditabilitycited by 16
  8. 2021Auditing E-Commerce Platforms for Algorithmically Curated Vaccine Misinformationcited by 11
  9. 2019Auditing News Curation Systems: A Case Study Examining Algorithmic and Editorial Logic in Apple Newscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 12; 2026: 13.

29 papers.

Sort:

By area:

  1. 2024LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actionscited by 21
  2. 2025Silenced Biases: The Dark Side LLMs Learned to Refusecited by 10
  3. 2025DAIQ: Auditing Demographic Attribute Inference from Question in LLMscited by 9
  4. 2024Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolutioncited by 7
  5. 2025Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Managementcited by 7
  6. 2025Rethinking LLM Bias Probing Using Lessons from the Social Sciencescited by 6
  7. 2025Fragile Preferences: A Deep Dive Into Order Effects in Large Language Modelscited by 4
  8. 2024Identity-related Speech Suppression in Generative AI Content Moderationcited by 3
  9. 2025Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolutioncited by 3
  10. 2025Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupationscited by 3
  11. 2026Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Biascited by 3
  12. 2024Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistancecited by 2
17 more
  1. 2025Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMscited by 2
  2. 2026FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocationcited by 2
  3. 2026Emergence of Biased Consensus in Multi-Agent LLM Debatescited by 2
  4. 2026PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Datasetcited by 1
  5. 2026Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiringcited by 1
  6. 2026Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflowscited by 1
  7. 2025Assessing Agentic Large Language Models in Multilingual National Biascited by 0
  8. 2025Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corporacited by 0
  9. 2025Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisationcited by 0
  10. 2025HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deploymentcited by 0
  11. 2026Evaluating LLM Behavior in Hiring: Implicit Weights, Fairness Across Groups, and Alignment with Human Preferencescited by 0
  12. 2026How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applicationscited by 0
  13. 2026Side-by-side Comparison Amplifies Dialect Bias in Language Modelscited by 0
  14. 2026The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Datacited by 0
  15. 2026The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Auditscited by 0
  16. 2026Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiringcited by 0
  17. 2026Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumescited by 0