# Identifying and Improving Disability Bias in GPT-Based Resume Screening

arXiv: https://arxiv.org/abs/2402.01732 · HTML: https://mlsanity.com/paper/2402.01732/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 97 references that are in the map.
- First posted on arXiv 28 Jan 2024.

## Builds on (most cited first, 13 of 13)

- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)
- [Revealing Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2104.08728/) (2021)
- [Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens](https://mlsanity.com/paper/2110.00521/) (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)
- [Characterizing Bias in Classifiers using Generative Models](https://mlsanity.com/paper/1906.11891/) (2019)
- [Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models](https://mlsanity.com/paper/2109.03300/) (2021)
- [Bias in Multimodal AI: Testbed for Fair Automatic Recruitment](https://mlsanity.com/paper/2004.07173/) (2020)
- [Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI](https://mlsanity.com/paper/2305.10566/) (2023)
- [Enhancing Job Recommendation through LLM-based Generative Adversarial Networks](https://mlsanity.com/paper/2307.10747/) (2023)
- [AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics](https://mlsanity.com/paper/2308.14608/) (2023)
- [An Autoethnographic Case Study of Generative Artificial Intelligence's Utility for Accessibility](https://mlsanity.com/paper/2308.09924/) (2023)
- [Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks](https://mlsanity.com/paper/2010.02419/) (2020)

## Built on by (most cited first, 28 of 28)

- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)
- [Natural Language Processing for Human Resources: A Survey](https://mlsanity.com/paper/2410.16498/) (2024)
- [No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy](https://mlsanity.com/paper/2509.04404/) (2025)
- [Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs](https://mlsanity.com/paper/2601.03087/) (2026)
- [Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors](https://mlsanity.com/paper/2409.18203/) (2024)
- [AccessEval: Benchmarking Disability Bias in Large Language Models](https://mlsanity.com/paper/2509.22703/) (2025)
- [Disability Representations: Finding Biases in Automatic Image Generation](https://mlsanity.com/paper/2406.14993/) (2024)
- [The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection](https://mlsanity.com/paper/2506.00256/) (2025)
- [Using ChatGPT to Score Essays and Short-Form Constructed Responses](https://mlsanity.com/paper/2408.09540/) (2024)
- [Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond](https://mlsanity.com/paper/2507.08866/) (2025)
- [When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applications](https://mlsanity.com/paper/2602.00044/) (2026)
- [Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts](https://mlsanity.com/paper/2501.04316/) (2025)
- [Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableism](https://mlsanity.com/paper/2505.20500/) (2025)
- ["I Hadn't Thought About That": Creators of Human-like AI Weigh in on Ethics And Neurodivergence](https://mlsanity.com/paper/2506.12098/) (2025)
- ["Accessibility people, you go work on that thing of yours over there": Addressing Disability Inclusion in AI Product Organizations](https://mlsanity.com/paper/2508.16607/) (2025)
- [NeuroBridge: Using Generative AI to Bridge Cross-neurotype Communication Differences through Neurotypical Perspective-taking](https://mlsanity.com/paper/2509.23434/) (2025)
- [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)
- [Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models](https://mlsanity.com/paper/2509.00963/) (2025)
- [Prompt injections as a tool for preserving identity in GAI image descriptions](https://mlsanity.com/paper/2510.16128/) (2025)
- [Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Education](https://mlsanity.com/paper/2601.14506/) (2026)
- [Investigating Disability Representations in Text-to-Image Models](https://mlsanity.com/paper/2602.04687/) (2026)
- [AutoScreen-FW: An LLM-based Framework for Resume Screening](https://mlsanity.com/paper/2603.18390/) (2026)
- [How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applications](https://mlsanity.com/paper/2604.22679/) (2026)
- [Cripping AI: Reimagining AI Through Lived Disability Experiences](https://mlsanity.com/paper/2605.02080/) (2026)
- [Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs](https://mlsanity.com/paper/2605.20191/) (2026)
- [Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed](https://mlsanity.com/paper/2607.24898/) (2026)
- [Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities](https://mlsanity.com/paper/2607.26062/) (2026)

## Abstract (arXiv)

As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human bias.