分析大模型对颜色的社会偏见，发现其存在与性别种族类似的刻板印象。
A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language Models
- 基于刻板印象内容模型设计新评估方法
- 8个大模型均表现出颜色刻板印象
- 模型架构和参数量影响偏见程度
随着大规模视觉语言模型（LVLM）的快速发展，其学习并生成社会偏见与刻板印象的潜在风险日益受到关注。以往研究在评估刻板印象时存在两大局限：忽视了关键词的重要性，以及未考虑颜色的影响。为此，本研究引入基于刻板印象内容模型（SCM）的新评估指标，并提出BASIC基准，用于评估性别、种族和颜色相关的刻板印象。利用SCM指标和BASIC，我们对8个LVLM进行了研究，发现：(1) 基于SCM的评估方法能有效捕捉刻板印象；(2) LVLM在输出中不仅存在性别和种族刻板印象，还表现出颜色刻板印象；(3) 模型架构与参数规模之间的交互作用似乎影响刻板印象的强弱。BASIC基准已公开发布。
原文摘要 · Abstract (English)
As large vision language models(LVLMs) rapidly advance, concerns about their potential to learn and generate social biases and stereotypes are increasing. Previous studies on LVLM's stereotypes face two primary limitations: metrics that overlooked the importance of content words, and datasets that overlooked the effect of color. To address these limitations, this study introduces new evaluation metrics based on the Stereotype Content Model (SCM). We also propose BASIC, a benchmark for assessing gender, race, and color stereotypes. Using SCM metrics and BASIC, we conduct a study with eight LVLMs to discover stereotypes. As a result, we found three findings. (1) The SCM-based evaluation is effective in capturing stereotypes. (2) LVLMs exhibit color stereotypes in the output along with gender and race ones. (3) Interaction between model architecture and parameter sizes seems to affect stereotypes. We release BASIC publicly on [anonymized for review].
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。