Qwen Councils
0

2026-01-02 08:18 UTC · cs.CL · cs.CL, cs.AI

ChiEngMixBench: Evaluating Large Language Models on Spontaneous and Natural Chinese-English Code-Mixed Generation

Qingyan Yang, Tongxi Wang, Yunsheng Luo

Code-mixing is increasingly prevalent in interactions between humans and large language models, yet existing work often reduces it to a translation or convertibility problem, making it difficult to assess whether a model's switching behavior is context-appropriate and aligned with human conventions. We introduce ChiEngMixBench, the first benchmark designed to evaluate code-mixing ability in authentic community contexts, built upon a general construction pipeline that enables scalable dataset development across domains and bilingual pairs. ChiEngMixBench formulates code-mixing as a cognitive alignment problem, characterized by two complementary signals: Spontaneity and Naturalness. Empirical evaluation shows that our metrics can systematically distinguish code-mixing performance across models. Beyond benchmarking, we further uncover an implicitly emergent Terminology Layering Strategy, a phenomenon consistent with the Matrix Language Frame (MLF) theory, indicating structured cognitive alignment between multilingual large language models and human communication.
arXiv abstractPDF

Comments

Log in to comment, reply, and vote.

No comments yet.