检测视觉语言模型在性别种族上的显性和隐性偏见。
VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
- 设计显性测试：通过图像问答和对比提问探查模型有意识偏见。
- 构建隐性任务：分析描述与表单生成中不同群体的文本差异。
- 评估5个主流模型，开源数据代码，适合关注AI公平性的研究者。
本研究探究视觉语言模型（VLMs）在性别和种族方面的显性和隐性社会偏见。显性偏见指有意识的判断，隐性偏见则潜藏于无意识响应中。针对显性偏见，设计两类任务：基于图像的多选题（如‘图中人物教育水平如何？’）和双图对比题（如‘第一张图中的人比第二张更受教育吗？’）。针对隐性偏见，设计两类任务：要求模型描述图像中人物，分析不同人口群体间的文本线索差异；以及生成包含20个属性的个人信息表单，考察属性间的关联是否存在偏见。评估了Gemini-1.5、GPT-4V、GPT-4o、LLaMA-3.2-Vision和LLaVA-v1.6五款模型。相关代码与数据已公开于https://github.com/uscnlp-lime/VisBias。
原文摘要 · Abstract (English)
This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Multiple-choice questions based on a given image (e.g., "What is the education level of the person in the image?") (2) Yes-No comparisons using two images (e.g., "Is the person in the first image more educated than the person in the second image?") For implicit bias, we design tasks where VLMs assist users but reveal biases through their responses: (1) Image description tasks: Models are asked to describe individuals in images, and we analyze disparities in textual cues across demographic groups. (2) Form completion tasks: Models draft a personal information collection form with 20 attributes, and we examine correlations among selected attributes for potential biases. We evaluate Gemini-1.5, GPT-4V, GPT-4o, LLaMA-3.2-Vision and LLaVA-v1.6. Our code and data are publicly available at https://github.com/uscnlp-lime/VisBias.
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。