mlsanityData to 7 Oct 2026

Identifying and Improving Disability Bias in GPT-Based Resume Screening

arXiv 2402.01732 ↗First posted 28 Jan 2024cs.CY cs.AIcited by 27

Not on the map. Why?

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.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 13 of its 97 references that are in the map. First posted on arXiv 28 Jan 2024.

Builds on

13 of 97 references.

References · 13

  1. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  2. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  3. 2021Revealing Persona Biases in Dialogue Systemscited by 33
  4. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  5. 2019Characterizing Bias in Classifiers using Generative Modelscited by 23
  6. 2021Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelscited by 23
  7. 2023Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPTcited by 23
  8. 2020Bias in Multimodal AI: Testbed for Fair Automatic Recruitmentcited by 21
  9. 2023Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AIcited by 19
  10. 2023Enhancing Job Recommendation through LLM-based Generative Adversarial Networkscited by 14
  11. 2023AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topicscited by 12
  12. 2023An Autoethnographic Case Study of Generative Artificial Intelligence's Utility for Accessibilitycited by 6
1 more
  1. 2020Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 11; 2026: 12.

27 papers.

Sort:

By area:

  1. 2025Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Modelscited by 30
  2. 2024Natural Language Processing for Human Resources: A Surveycited by 9
  3. 2025No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomycited by 8
  4. 2026Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMscited by 6
  5. 2024Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviorscited by 5
  6. 2025AccessEval: Benchmarking Disability Bias in Large Language Modelscited by 5
  7. 2024Disability Representations: Finding Biases in Automatic Image Generationcited by 4
  8. 2025The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selectioncited by 3
  9. 2024Using ChatGPT to Score Essays and Short-Form Constructed Responsescited by 2
  10. 2025Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyondcited by 2
  11. 2026When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applicationscited by 2
  12. 2025Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contextscited by 1
15 more
  1. 2025Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableismcited by 1
  2. 2025"I Hadn't Thought About That": Creators of Human-like AI Weigh in on Ethics And Neurodivergencecited by 1
  3. 2025"Accessibility people, you go work on that thing of yours over there": Addressing Disability Inclusion in AI Product Organizationscited by 1
  4. 2025NeuroBridge: Using Generative AI to Bridge Cross-neurotype Communication Differences through Neurotypical Perspective-takingcited 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. 2025Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Modelscited by 0
  8. 2026Compounding Disadvantage: Auditing Intersectional Bias in LLM-Generated Explanations Across Indian and American STEM Educationcited by 0
  9. 2026Investigating Disability Representations in Text-to-Image Modelscited by 0
  10. 2026AutoScreen-FW: An LLM-based Framework for Resume Screeningcited by 0
  11. 2026How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applicationscited by 0
  12. 2026Cripping AI: Reimagining AI Through Lived Disability Experiencescited by 0
  13. 2026Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMscited by 0
  14. 2026Harm is not Universal: Community-Specific Toxicity Detection is Urgently Neededcited by 0
  15. 2026Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilitiescited by 0