Made in China, Aligned with the USA: Chinese LLMs Express Similar Moral Values to American People

ACL ARR 2026 January Submission4697 Authors

Keywords: large language models, value alignment, East meets West, moral foundations, world values survey

Abstract: Many studies have reported that large language models (LLMs) tend to express similar values to people from Western countries, such as prioritizing individualism over collectivism. However, evidence for this ethical bias comes mostly from LLMs made by American companies. The current crop of state-of-the-art models includes several made in China, so we conducted the first large-scale investigation of how models made in China and the USA align with people from China and the USA. We elicited responses from ten Chinese models and ten American models to the Moral Foundations Questionnaire 2.0 and the World Values Survey, two well-validated measures with responses from thousands of Chinese and American people. We found that all models respond to both surveys more like American people than like Chinese people. This skew toward American responses is only slightly mitigated when prompting the models in Chinese or imposing a Chinese persona on the models. Given that LLMs may serve as tools for soft power competition between China and the USA, this persistent alignment with Americans may have important implications for geopolitics, and given that LLMs already help people make decisions, it has important implications for daily life.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: ethical considerations in NLP applications, policy and governance, model bias/fairness evaluation, model bias/unfairness mitigation

Contribution Types: Model analysis & interpretability, Data analysis, Theory

Languages Studied: English, Chinese

Submission Number: 4697