大型语言模型中的锚定偏差：一项实验研究
Anchoring Bias in Large Language Models: An Experimental Study
AI总结：
本研究通过实验探讨了大型语言模型中的锚定偏差，发现模型对偏差提示敏感，且需从多角度收集提示以缓解该偏差，而思维链等简单算法效果不足。
摘要：
GPT-4和Gemini等大型语言模型（LLMs）通过使机器生成和理解类人文本，显著推动了人工智能的发展。尽管LLMs能力令人瞩目，但并非不受限制，包括各种偏差。尽管许多研究探讨了人口统计学偏差，但LLMs中的认知偏差却未受到同等审视。本研究深入探讨了锚定偏差，这是一种初始信息对判断产生不成比例影响的认知偏差。利用一个实验数据集，我们考察了锚定偏差在LLMs中的表现，并验证了各种缓解策略的有效性。我们的发现突出了LLM响应对偏差提示的敏感性。同时，实验表明，为缓解锚定偏差，需要从全面角度收集提示，以防止LLMs被锚定到个别信息上，而思维链、原则思考、忽略锚定提示和反思等简单算法则不足以应对。
英文摘要：
Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to limitations, including various biases. While much research has explored demographic biases, the cognitive biases in LLMs have not been equally scrutinized. This study delves into anchoring bias, a cognitive bias where initial information disproportionately influences judgment. Utilizing an experimental dataset, we examine how anchoring bias manifests in LLMs and verify the effectiveness of various mitigation strategies. Our findings highlight the sensitivity of LLM responses to biased hints. At the same time, our experiments show that, to mitigate anchoring bias, one needs to collect hints from comprehensive angles to prevent the LLMs from being anchored to individual pieces of information, while simple algorithms such as Chain-of-Thought, Thoughts of Principles, Ignoring Anchor Hints, and Reflection are not sufficient.
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。
