通过推理依赖生成缓解LLM中的选择支持性偏见
Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation
AI总结：
本文提出通过推理依赖生成缓解LLM中选择支持性偏见的方法，生成无偏推理数据并提升模型在决策任务中的表现。
摘要：
最近的研究表明，一些大语言模型在进行评估时会表现出选择支持性偏见（CSB），系统性地倾向于其选择的选项，可能影响人工智能辅助决策的客观性。尽管现有的去偏方法主要针对人口和社会偏见，但针对LLM中认知偏见的方法仍鲜有探索。在本工作中，我们提出了首个通过推理依赖生成（RDG）解决CSB的解决方案，这是一种生成无偏推理数据的新型框架，通过微调来缓解选择支持性偏见。RDG自动构建平衡的推理问答对，明确（不）建模选择、证据和论证之间的依赖关系。我们的方法能够生成跨领域的大量问答对数据集，包含上下文依赖数据和依赖解耦数据。实验表明，经过RDG生成数据微调的LLM在基于记忆的实验中提升了81.5%，在基于评估的实验中提升了94.3%，同时在标准BBQ基准测试中保持了相似的性能。本工作开创了针对LLM认知偏见的解决方法，并推动了更可靠的AI辅助决策支持系统的发展。
英文摘要：
Recent studies have demonstrated that some Large Language Models exhibit choice-supportive bias (CSB) when performing evaluations, systematically favoring their chosen options and potentially compromising the objectivity of AI-assisted decision making. While existing debiasing approaches primarily target demographic and social biases, methods for addressing cognitive biases in LLMs remain largely unexplored. In this work, we present the first solution to address CSB through Reasoning Dependency Generation (RDG), a novel framework for generating unbiased reasoning data to mitigate choice-supportive bias through fine-tuning. RDG automatically constructs balanced reasoning QA pairs, explicitly (un)modeling the dependencies between choices, evidences, and justifications. Our approach is able to generate a large-scale dataset of QA pairs across domains, incorporating Contextual Dependency Data and Dependency Decouple Data. Experiments show that LLMs fine-tuned on RDG-generated data demonstrate a 81.5% improvement in memory-based experiments and 94.3% improvement in the evaluation-based experiment, while maintaining similar performance on standard BBQ benchmarks. This work pioneers an approach for addressing cognitive biases in LLMs and contributes to the development of more reliable AI-assisted decision support systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
