视觉语言模型中的文化意识：一项跨国家探索
Cultural Awareness in Vision-Language Models: A Cross-Country Exploration
AI总结：
本研究提出新框架，通过三项检索任务系统评估视觉语言模型在跨国家背景下对种族、性别和身体特征的文化偏见，发现模型存在持续刻板印象关联。
摘要：
视觉语言模型（VLMs）正越来越多地部署于多元文化背景中，然而其内部偏见仍未得到充分理解。在本工作中，我们提出了一个新框架，用以系统评估视觉语言模型如何编码跨国家的、与种族、性别和身体特征相关的文化差异和偏见。我们引入了三项基于检索的任务：（1）种族到国家检索，考察特定种族群体（东亚人、白人、中东人、拉丁裔、南亚人和黑人）个体与不同国家之间的关联；（2）个人特质到国家检索，将图像与基于特质的提示（如聪明、诚实、犯罪、暴力）配对，以调查潜在的刻板印象关联；（3）身体特征到国家检索，聚焦于瘦、年轻、肥胖和年老等视觉属性，探索身体外貌如何与文化上与国家相关联。我们的研究结果揭示了视觉语言模型中持续存在的偏见，突显了视觉表征可能无意中强化社会刻板印象。
英文摘要：
Vision-Language Models (VLMs) are increasingly deployed in diverse cultural contexts, yet their internal biases remain poorly understood. In this work, we propose a novel framework to systematically evaluate how VLMs encode cultural differences and biases related to race, gender, and physical traits across countries. We introduce three retrieval-based tasks: (1) Race to Country retrieval, which examines the association between individuals from specific racial groups (East Asian, White, Middle Eastern, Latino, South Asian, and Black) and different countries; (2) Personal Traits to Country retrieval, where images are paired with trait-based prompts (e.g., Smart, Honest, Criminal, Violent) to investigate potential stereotypical associations; and (3) Physical Characteristics to Country retrieval, focusing on visual attributes like skinny, young, obese, and old to explore how physical appearances are culturally linked to nations. Our findings reveal persistent biases in VLMs, highlighting how visual representations may inadvertently reinforce societal stereotypes.
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。
