用多智能体框架在不降性能前提下，大幅降低大模型社会偏见。
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
- 设计多智能体系统对输入中的偏见内容进行因果干预。
- 在两个数据集上偏见分数降低最高达87.7%，性能下降不足6.8%。
- 适合关注模型公平性且不愿牺牲准确率的研究者使用。
自然语言处理领域因大语言模型（LLMs）的发展取得显著进展，但这些模型常产生社会偏见输出。现有研究多通过提示使模型行为符合伦理，但导致性能明显下降。本文提出一种多目标多智能体框架（MOMA），在不显著影响性能的前提下缓解大模型的社会偏见。其核心思想是部署多个智能体对输入问题中与偏见相关的部分实施因果干预，打破这些内容与答案间的捷径关联。实验在两个数据集和两个模型上进行，结果显示，MOMA可将偏见分数降低最多87.7%，在BBQ数据集上性能下降不超过6.8%；同时在StereoSet数据集上，多目标指标icat提升高达58.1%。代码将公开于https://github.com/Cortantse/MOMA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。