Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Zhenjie, Chen, Wenqing, Tang, Yi, Li, Xuanying, Hu, Cheng, Chu, Zhixuan, Ren, Kui, Zheng, Zibin, Lu, Zhichao
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.15504
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916609688338432
author Xu, Zhenjie
Chen, Wenqing
Tang, Yi
Li, Xuanying
Hu, Cheng
Chu, Zhixuan
Ren, Kui
Zheng, Zibin
Lu, Zhichao
author_facet Xu, Zhenjie
Chen, Wenqing
Tang, Yi
Li, Xuanying
Hu, Cheng
Chu, Zhixuan
Ren, Kui
Zheng, Zibin
Lu, Zhichao
contents Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted on two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%. Code will be made available at https://github.com/Cortantse/MOMA.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
Xu, Zhenjie
Chen, Wenqing
Tang, Yi
Li, Xuanying
Hu, Cheng
Chu, Zhixuan
Ren, Kui
Zheng, Zibin
Lu, Zhichao
Computation and Language
Natural language processing (NLP) has seen remarkable advancements with the development of large language models (LLMs). Despite these advancements, LLMs often produce socially biased outputs. Recent studies have mainly addressed this problem by prompting LLMs to behave ethically, but this approach results in unacceptable performance degradation. In this paper, we propose a multi-objective approach within a multi-agent framework (MOMA) to mitigate social bias in LLMs without significantly compromising their performance. The key idea of MOMA involves deploying multiple agents to perform causal interventions on bias-related contents of the input questions, breaking the shortcut connection between these contents and the corresponding answers. Unlike traditional debiasing techniques leading to performance degradation, MOMA substantially reduces bias while maintaining accuracy in downstream tasks. Our experiments conducted on two datasets and two models demonstrate that MOMA reduces bias scores by up to 87.7%, with only a marginal performance degradation of up to 6.8% in the BBQ dataset. Additionally, it significantly enhances the multi-objective metric icat in the StereoSet dataset by up to 58.1%. Code will be made available at https://github.com/Cortantse/MOMA.
title Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
topic Computation and Language
url https://arxiv.org/abs/2412.15504