Scholarlink

<p>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 without limitations. They exhibit various biases. Although much research has explored demographic biases, cognitive biases in LLM have not been equally studied. This study delves into anchoring bias, a cognitive bias in which initial information disproportionately influences judgment. Using an experimental data set, we examine how anchoring bias manifests in LLM and verify the effectiveness of various mitigation strategies. Our findings highlight the sensitivity of LLM responses to biased prompts. At the same time, our experiments show that to mitigate anchoring bias, one needs to collect information from comprehensive angles to prevent the LLMs from being anchored to individual pieces of information, as simple algorithms such as Chain-of-Thought, Thoughts of Principles, Ignoring Anchor Hints, and Reflection are insufficient.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Anchoring bias in large language models: an experimental study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月5日

查看全文
  • Jiaxu Lou,
  • Yifan Sun

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 without limitations. They exhibit various biases. Although much research has explored demographic biases, cognitive biases in LLM have not been equally studied. This study delves into anchoring bias, a cognitive bias in which initial information disproportionately influences judgment. Using an experimental data set, we examine how anchoring bias manifests in LLM and verify the effectiveness of various mitigation strategies. Our findings highlight the sensitivity of LLM responses to biased prompts. At the same time, our experiments show that to mitigate anchoring bias, one needs to collect information from comprehensive angles to prevent the LLMs from being anchored to individual pieces of information, as simple algorithms such as Chain-of-Thought, Thoughts of Principles, Ignoring Anchor Hints, and Reflection are insufficient.