偏见与推理的力学：分析链式推理提示对大语言模型中性别偏见的影响
Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
AI总结：
本文研究了链式推理提示对大语言模型中性别偏见的影响，结合基准测试评估与机制可解释性技术，发现链式推理并未有效减少偏见，偏见仍存在于隐藏表示中。
摘要：
尽管有大量文献表明大型语言模型（LLMs）在社会敏感领域得到广泛应用，但它们仍编码了性别偏见。链式推理（CoT）提示已被提出作为减轻偏见的方法。然而，现有评估主要关注LLM基准性能的变化，提供了有限的关于模型内部机制是否真正改变的见解。在本文中，我们研究了链式推理提示如何影响LLM中的性别偏见，结合基准测试评估与机制可解释性技术以及推理链失败分析。我们的结果证实了LLM输出中存在刻板印象偏见，显示链式推理提示并未一致减少偏见差距。机制分析显示，尽管链式推理在某些注意力头集群中平衡了偏见行为，但性别偏见仍嵌入在隐藏表示中，表明仅是表面缓解。对推理链的检查进一步表明，这些改进源于对数据集的记忆和熟悉，而非对偏见的真实理解。
英文摘要：
Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach. However, existing evaluations primarily focus on changes in LLM benchmark performance, providing limited insight into whether apparent bias reductions reflect meaningful changes in a model's internal mechanisms. In this work, we investigate how CoT prompting affects gender bias in LLMs, combining benchmark-based evaluation with mechanistic interpretability techniques and reasoning chain failure analysis. Our results confirm a stereotypical bias present in LLM outputs across benchmarks, showing that CoT prompting does not consistently reduce the bias gap. Mechanistic analyses reveal that although CoT balances biased behavior in certain attention head clusters, gender bias remains embedded in hidden representations, indicating only superficial mitigation. Inspection of reasoning chains further suggests that these improvements stem from memorization and familiarity with the dataset rather than genuine understanding of bias.
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。
