When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models

TL;DR

This study systematically examined whether leading AI language models reflect Western individualist biases over local cultural values, revealing a systemic homogenization of values across different societies.

Contribution

It provides the first cross-cultural audit of large language models' value biases, highlighting their tendency to encode Western individualism regardless of user background.

Findings

AI models favor Western individualist advice over local cultural norms

Bias is most pronounced in Nigeria and India, less so in Japan

Models diverge in bias mechanisms depending on language and user input

Abstract

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sole exception: AI systems treated Japanese users as more group-oriented than surveys show, revealing that AI encodes outdated stereotypes.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.