注意手势：评估AI对文化冒犯性非语言手势的敏感性
Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
AI总结：
本研究引入MC-SIGNS数据集，评估AI对文化冒犯性手势的敏感性，发现T2I、LLM和VLM存在美国中心偏见，强调需开发文化感知的AI安全机制。
摘要：
手势是非语言交流中不可或缺的一部分，其含义因文化而异，误解可能带来严重的社会和外交后果。随着AI系统日益融入全球应用，确保它们不会无意中延续文化冒犯至关重要。为此，我们引入了多文化不当手势与非语言符号集（MC-SIGNS），这是一个包含288个手势-国家配对的数据集，针对25种手势和85个国家，标注了冒犯性、文化意义和情境因素。通过使用MC-SIGNS进行系统评估，我们发现了关键局限性：文本到图像（T2I）系统表现出强烈的美国中心偏见，在检测美国情境中的冒犯性手势时表现优于非美国情境；大型语言模型（LLM）倾向于过度标记手势为冒犯性；视觉-语言模型（VLM）在回应诸如祝福他人好运等普遍概念时，默认采用美国式解读，经常建议文化上不恰当的手势。这些发现凸显了迫切需要具有文化意识的AI安全机制，以确保AI技术的公平全球部署。
英文摘要：
Gestures are an integral part of non-verbal communication, with meanings that vary across cultures, and misinterpretations that can have serious social and diplomatic consequences. As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical. To this end, we introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors across 25 gestures and 85 countries. Through systematic evaluation using MC-SIGNS, we uncover critical limitations: text-to-image (T2I) systems exhibit strong US-centric biases, performing better at detecting offensive gestures in US contexts than in non-US ones; large language models (LLMs) tend to over-flag gestures as offensive; and vision-language models (VLMs) default to US-based interpretations when responding to universal concepts like wishing someone luck, frequently suggesting culturally inappropriate gestures. These findings highlight the urgent need for culturally-aware AI safety mechanisms to ensure equitable global deployment of AI technologies.
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。
