Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach
It addresses bias in AI-generated content for queer representation, though it is incremental as it focuses on a specific aspect of bias mitigation.
This paper tackled the problem of biased pronoun usage in large language models (LLMs) that misrepresent queer individuals, and introduced a collaborative agent pipeline that improved inclusive pronoun classification by 32.6 percentage points over GPT-4o on the Tango dataset.
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.