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

arXiv: https://arxiv.org/abs/2405.04412 · HTML: https://mlsanity.com/paper/2405.04412/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 107 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 21 of 21)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models](https://mlsanity.com/paper/2102.04130/) (2021)
- [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models](https://mlsanity.com/paper/2208.07852/) (2022)
- [AI auditing: The Broken Bus on the Road to AI Accountability](https://mlsanity.com/paper/2401.14462/) (2024)
- [What does it mean to solve the problem of discrimination in hiring? Social, technical and legal perspectives from the UK on automated hiring systems](https://mlsanity.com/paper/1910.06144/) (2019)
- [Intersectional Bias in Causal Language Models](https://mlsanity.com/paper/2107.07691/) (2021)
- [Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT](https://mlsanity.com/paper/2310.05135/) (2023)
- [Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity](https://mlsanity.com/paper/2302.12832/) (2023)
- [Auditing Work: Exploring the New York City algorithmic bias audit regime](https://mlsanity.com/paper/2402.08101/) (2024)
- [A Silicon Valley Love Triangle: Hiring Algorithms, Pseudo-Science, and the Quest for Auditability](https://mlsanity.com/paper/2106.12403/) (2021)
- [Auditing E-Commerce Platforms for Algorithmically Curated Vaccine Misinformation](https://mlsanity.com/paper/2101.08419/) (2021)
- [Auditing News Curation Systems: A Case Study Examining Algorithmic and Editorial Logic in Apple News](https://mlsanity.com/paper/1908.00456/) (2019)

## Built on by (most cited first, 29 of 29)

- [LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions](https://mlsanity.com/paper/2406.08824/) (2024)
- [DAIQ: Auditing Demographic Attribute Inference from Question in LLMs](https://mlsanity.com/paper/2508.15830/) (2025)
- [Silenced Biases: The Dark Side LLMs Learned to Refuse](https://mlsanity.com/paper/2511.03369/) (2025)
- [Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution](https://mlsanity.com/paper/2408.17285/) (2024)
- [Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management](https://mlsanity.com/paper/2502.10407/) (2025)
- [Rethinking LLM Bias Probing Using Lessons from the Social Sciences](https://mlsanity.com/paper/2503.00093/) (2025)
- [Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models](https://mlsanity.com/paper/2506.14092/) (2025)
- [Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias](https://mlsanity.com/paper/2601.18486/) (2026)
- [Identity-related Speech Suppression in Generative AI Content Moderation](https://mlsanity.com/paper/2409.13725/) (2024)
- [Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution](https://mlsanity.com/paper/2508.07111/) (2025)
- [Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations](https://mlsanity.com/paper/2510.21011/) (2025)
- [Emergence of Biased Consensus in Multi-Agent LLM Debates](https://mlsanity.com/paper/2608.02827/) (2026)
- [Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance](https://mlsanity.com/paper/2410.17333/) (2024)
- [Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs](https://mlsanity.com/paper/2505.23996/) (2025)
- [FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation](https://mlsanity.com/paper/2607.28934/) (2026)
- [PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset](https://mlsanity.com/paper/2603.22714/) (2026)
- [Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring](https://mlsanity.com/paper/2604.19984/) (2026)
- [Resume-ing Control: (Mis)Perceptions of Agency Around GenAI Use in Recruiting Workflows](https://mlsanity.com/paper/2604.26851/) (2026)
- [Assessing Agentic Large Language Models in Multilingual National Bias](https://mlsanity.com/paper/2502.17945/) (2025)
- [Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora](https://mlsanity.com/paper/2508.13169/) (2025)
- [Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation](https://mlsanity.com/paper/2509.09735/) (2025)
- [HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment](https://mlsanity.com/paper/2510.12217/) (2025)
- [Evaluating LLM Behavior in Hiring: Implicit Weights, Fairness Across Groups, and Alignment with Human Preferences](https://mlsanity.com/paper/2601.11379/) (2026)
- [How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applications](https://mlsanity.com/paper/2604.22679/) (2026)
- [Side-by-side Comparison Amplifies Dialect Bias in Language Models](https://mlsanity.com/paper/2605.24384/) (2026)
- [The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data](https://mlsanity.com/paper/2608.04268/) (2026)
- [The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits](https://mlsanity.com/paper/2609.09048/) (2026)
- [Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring](https://mlsanity.com/paper/2609.22169/) (2026)
- [Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes](https://mlsanity.com/paper/2609.22188/) (2026)

## 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.