Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

ACL ARR 2026 January Submission5518 Authors

Keywords: Chinese Large Language Models (LLMs), Social Bias, Fairness, Ingroup–Outgroup Framing

Abstract: Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases. We investigate social identity biases in Chinese LLMs using Mandarin-specific prompts across ten representative models. Our evaluation compares ingroup (“We”) and outgroup (“They”) framings across 240 social groups salient in the Chinese context, using a two-tiered measurement framework that assesses both sentiment and toxicity. The prompt design explicitly accounts for linguistic and cultural properties of Mandarin, such as Chinese-specific gendered pronoun usage, enabling a controlled comparison of social identity framing effects. Across models, we observe consistent patterns of ingroup solidarity and outgroup hostility, indicating systematic social identity biases in Chinese LLMs. Our study introduces a language-aware evaluation framework for Chinese LLMs and shows that social identity biases previously documented in English also manifest in Chinese, highlighting the cross-linguistic relevance of bias concerns in large language models.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: Chinese Large Language Models (LLMs), Social Bias, Fairness, Ingroup–Outgroup Framing

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: Mandarin Chinese, English

Submission Number: 5518