Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach

Tianyi Huang, Arya Somasundaram
11/12/2024
cs.CLcs.MA

No official code found. Best implementation: Tonyhrule/Queer-Bias-LLMs (3 stars, MIT, last commit 2024-11-13).

Abstract

Large Language Models (LLMs) often perpetuate biases in pronoun usage, leading to misrepresentation or exclusion of queer individuals. This paper addresses the specific problem of biased pronoun usage in LLM outputs, particularly the inappropriate use of traditionally gendered pronouns ("he," "she") when inclusive language is needed to accurately represent all identities. We introduce a collaborative agent pipeline designed to mitigate these biases by analyzing and optimizing pronoun usage for inclusivity. Our multi-agent framework includes specialized agents for both bias detection and correction. Experimental evaluations using the Tango dataset-a benchmark focused on gender pronoun usage-demonstrate that our approach significantly improves inclusive pronoun classification, achieving a 32.6 percentage point increase over GPT-4o in correctly disagreeing with inappropriate traditionally gendered pronouns $(χ^2 = 38.57, p < 0.0001)$. These results accentuate the potential of agent-driven frameworks in enhancing fairness and inclusivity in AI-generated content, demonstrating their efficacy in reducing biases and promoting socially responsible AI.

View on arXivView PDF

Code Implementations(1)

Tonyhrule/Queer-Bias-LLMsCommunity100%
MIT

This project implements a collaborative agent pipeline to detect and reduce biases in large language model outputs, focusing on improving pronoun inclusivity and fair queer representation

30PythonOct 8, 20241 years agoMIT
artificial-intelligencebias-mitigationmultiagent-systems

Similar Papers

Do They Understand Them? An Updated Evaluation on Nonbinary Pronoun Handling in Large Language Models

89% match2025

From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs

86% match2024

Evaluating Gender Bias in Large Language Models

85% match1 repo2024

PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs

85% match2025

LLM-Guided Synthetic Augmentation (LGSA) for Mitigating Bias in AI Systems

85% match2025

Generalizing Fairness to Generative Language Models via Reformulation of Non-discrimination Criteria

84% match1 repo12024

Cite this paper

@article{huang2024mitigating,
  title  = {Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach},
  author = {Tianyi Huang and Arya Somasundaram},
  year   = {2024},
  eprint = {2411.07656},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.07656v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.07656.svg)](https://codeofpaper.com/paper/2411.07656)

Discussion