标题： 显式与隐式：通过自我反思探究大型语言模型中的社会偏见 显示英文标题

标题： Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection

摘要： 大型语言模型（LLMs）在其生成的内容中已被证明表现出各种偏见和刻板印象。尽管已有大量研究调查了LLMs中的偏见，但以往的工作主要集中在显式偏见上，对隐式偏见以及这两种偏见之间的关系关注较少。本文提出了一种基于社会心理学理论的系统性框架，用于研究和比较LLMs中的显式和隐式偏见。我们提出了一个新颖的基于自我反思的评估框架，该框架分为两个阶段：首先通过模拟的心理评估方法测量隐式偏见，然后通过提示LLMs分析它们自己的生成内容来评估显式偏见。通过对多个社会维度上的先进LLMs进行广泛的实验，我们表明LLMs在显式和隐式偏见之间存在显著不一致：虽然显式偏见表现为轻微的刻板印象，但隐式偏见表现出强烈的刻板印象。我们进一步研究导致这种显式-隐式偏见不一致的潜在因素，考察了训练数据规模、模型大小和对齐技术的影响。实验结果显示，虽然显式偏见随着训练数据量和模型规模的增加而减少，但隐式偏见呈现出相反的上升趋势。此外，当代的对齐方法有效地抑制了显式偏见，但在减轻隐式偏见方面效果有限。 显示英文摘要

摘要： Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content. While extensive research has investigated biases in LLMs, prior work has predominantly focused on explicit bias, with minimal attention to implicit bias and the relation between these two forms of bias. This paper presents a systematic framework grounded in social psychology theories to investigate and compare explicit and implicit biases in LLMs. We propose a novel self-reflection-based evaluation framework that operates in two phases: first measuring implicit bias through simulated psychological assessment methods, then evaluating explicit bias by prompting LLMs to analyze their own generated content. Through extensive experiments on advanced LLMs across multiple social dimensions, we demonstrate that LLMs exhibit a substantial inconsistency between explicit and implicit biases: while explicit bias manifests as mild stereotypes, implicit bias exhibits strong stereotypes. We further investigate the underlying factors contributing to this explicit-implicit bias inconsistency, examining the effects of training data scale, model size, and alignment techniques. Experimental results indicate that while explicit bias declines with increased training data and model size, implicit bias exhibits a contrasting upward trend. Moreover, contemporary alignment methods effectively suppress explicit bias but show limited efficacy in mitigating implicit bias.