Exploring Covert Bias in Large Language Models - Experimental Evidence of Racial Discrimination in Resume Creation and Selection
Files
Date
2025-01-07
Authors
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Narrator
Transcriber
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
6519
Ending Page
Alternative Title
Abstract
Fine-tuning efforts have led to progress in reducing overt, obvious gender and racial biases in the latest generation of large language models (LLMs). Here we study covert, non-obvious bias in LLM-based chat systems. We run a two-stage experiment in the hiring context consisting of resume creation and selection. We use ChatGPT-4o to create resumes for minority, ethnic candidates and majority, baseline candidates. After removal of all identifying markers, we run pair-wise selection tests and find that resumes of majority candidates are stronger, winning contests in 80% of the time. This suggests that racial markers lead to encoding of biases in resume generation in imperceptible ways. Covert biases are difficult to spot and hard to address, but they deserve urgent attention, as the latest models are becoming increasingly capable of inferring user characteristics from conversations, potentially biasing content in unwanted and unexpected ways. We discuss implications and avenues for future research.
Description
Keywords
AI and Digital Discrimination, bias, covert bias, hiring, llms, resume selection
Citation
Extent
10
Format
Geographic Location
Time Period
Related To
Proceedings of the 58th Hawaii International Conference on System Sciences
Related To (URI)
Table of Contents
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Local Contexts
Collections
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.