STEREODISCO：发现大语言模型中的刻板印象

中文摘要 AI 辅助

大语言模型（LLMs）会编码、传递并延续刻板印象。现有计算研究聚焦于社会心理学中少量语义轴，且基于语言模型生成的词嵌入开展研究，仍有其他哪些语义轴在LLMs中带有刻板印象关联、以及LLMs如何在内部表征这些轴的问题未得到解决。本文提出STEREODISCO框架，该框架将语义差异法（Osgood等人，1957）适配于对LLMs内部表征中刻板印象的系统研究。STEREODISCO从WordNet反义词同义集中构建约2000个候选语义轴，通过探测将每个候选轴恢复为LLM激活空间中的几何轴，并通过对概念投影的统计检验识别出带有刻板印象的轴。作为案例研究，本文将STEREODISCO应用于LLAMA-3-8B-INSTRUCT和MISTRAL-7B-INSTRUCT的社会群体刻板印象研究，发现这两个LLM在社会群体评分上的一致性高于与人类的一致性，表明LLM编码的刻板印象内容与社会心理学记录的内容存在差异；还发现了现有研究未调查的刻板印象轴，包括谦逊与骄傲、狭隘与开明、怯懦与勇敢，这些轴已得到人类标注员的独立确认。

英文摘要

LLMs encode, convey, and perpetuate stereotypes. Prior computational research focuses on a small set of semantic axes investigated in social psychology, and operates on word embeddings produced by language models, leaving open which other semantic axes carry stereotypical associations in LLMs and how LLMs internally represent such axes. We introduce STEREODISCO, a framework that adapts the semantic differential method (Osgood et al., 1957) to the systematic study of stereotypes in LLM internal representations. STEREODISCO constructs approx. 2,000 candidate semantic axes from WordNet antonym synsets, recovers each as a geometric axis in the LLM's activation space via probing, and identifies stereotypical axes via a statistical test over concept projections. As a case study, we apply STEREODISCO to social group stereotypes with LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT. We find that the two LLMs agree with each other on social group ratings more than with humans, suggesting that LLM-encoded stereotype content diverges from that documented in social psychology. We also discover stereotypical axes not investigated in prior work -- including humble vs. proud, narrow-minded vs. broad-minded, and cowardly vs. brave, which human annotators independently confirm.

发表机构

• Institute for Artificial Intelligence（人工智能研究所）
• Institute for Social Science（社会科学研究所）
• University of Southampton（南安普顿大学）

机构由 AI 辅助整理，请以论文原文为准。