当AI说话时，它表达的是谁的价值观？对个体主义-集体主义偏见的跨文化审计
When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models
AI总结：
研究探讨了大型语言模型在不同文化背景下对个体主义与集体主义偏见的跨文化表现，发现AI系统倾向于提供西方个体主义建议，即使面对强调家庭和社区的文化，且日本例外，揭示AI编码了过时的刻板印象。
摘要：
当您向AI助手寻求职业、婚姻或家庭冲突的建议时，无论您来自哪里，它是否都会给出相同答案？我们通过向三个领先的AI系统（Claude Sonnet 4.5、GPT-5.4和Gemini 2.5 Flash）展示十个现实个人困境，针对来自10个国家、五个大洲的7种语言的用户（n=840评分响应）系统地测试了这一点。我们比较了AI建议与世界价值观调查第7波数据，测量每个国家人们实际上所相信的。所有三个AI系统都一致给出了西方风格的个体主义建议，即使对于优先考虑家庭、社区和权威的社会，其偏见显著大于本地价值观预测（均值差距+0.76在1-5量表上；t=15.65，p<0.001）。差距最大的是尼日利亚（+1.85）和印度（+0.82）。日本是唯一例外：AI系统将日本用户视为比调查显示的更群体导向，揭示AI编码了过时的刻板印象。Claude和GPT-5.4显示出几乎相同的偏见程度，而Gemini较低但仍然显著。这些模型在机制上有所不同：Claude在用户的母语中进一步转向集体主义；Gemini更倾向于个体主义；GPT-5.4仅响应于声明的国家身份。这些发现指向了前沿AI在价值观上的系统同质化。数据、代码和评分流程已公开发布。
英文摘要：
When you ask an AI assistant for advice about your career, your marriage, or a conflict with your family, does it give you the same answer regardless of where you are from? We tested this systematically by presenting three leading AI systems (Claude Sonnet 4.5, GPT-5.4, and Gemini 2.5 Flash) with ten real-life personal dilemmas, framed for users from 10 countries across 5 continents in 7 languages (n=840 scored responses). We compared AI advice against World Values Survey Wave 7 data measuring what people in each country actually believe. All three AI systems consistently gave Western-style, individualist advice even to users from societies that prioritize family, community, and authority, significantly more so than local values would predict (mean gap +0.76 on a 1-5 scale; t=15.65, p<0.001). The gap is largest for Nigeria (+1.85) and India (+0.82). Japan is the sole exception: AI systems treated Japanese users as more group-oriented than surveys show, revealing that AI encodes outdated stereotypes. Claude and GPT-5.4 show nearly identical bias magnitude, while Gemini is lower but still significant. The models diverge in mechanism: Claude shifts further collectivist in the user's native language; Gemini shifts more individualist; GPT-5.4 responds only to stated country identity. These findings point to a systemic homogenization of values across frontier AI. Data, code, and scoring pipeline are openly released.
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。
