显式与隐式：通过自反思探究大语言模型中的社会偏见
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection
AI总结：
本文通过自反思框架系统比较LLMs的显式与隐式社会偏见，发现二者存在显著不一致，且对齐技术对隐式偏见效果有限。
摘要：
大语言模型（LLMs）已被证明在其生成内容中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，但先前的工作主要关注显式偏见，对隐式偏见以及这两种偏见形式之间关系的关注极少。本文提出了一个基于社会心理学理论的系统框架，用于调查和比较LLMs中的显式与隐式偏见。我们提出了一种新颖的基于自反思的评估框架，该框架分两个阶段运作：首先通过模拟心理评估方法测量隐式偏见，然后通过提示LLMs分析其自身生成的内容来评估显式偏见。通过在多个社会维度上对先进LLMs进行广泛实验，我们证明LLMs在显式与隐式偏见之间表现出显著的不一致性：显式偏见表现为轻微的刻板印象，而隐式偏见则表现出强烈的刻板印象。我们进一步调查了导致这种显式-隐式偏见不一致性的潜在因素，考察了训练数据规模、模型大小和对齐技术的影响。实验结果表明，虽然显式偏见随着训练数据和模型规模的增加而下降，但隐式偏见却呈现出相反的上升趋势。此外，当代对齐方法能有效抑制显式偏见，但在减轻隐式偏见方面效果有限。
英文摘要：
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.
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。
