Search Articles

View query in Help articles search

Search Results (1 to 10 of 1073 Results)

Download search results: CSV END BibTex RIS


Performance of Large Language Models in the Non-English Context: Qualitative Study of Models Trained on Different Languages in Chinese Medical Examinations

Performance of Large Language Models in the Non-English Context: Qualitative Study of Models Trained on Different Languages in Chinese Medical Examinations

The models tested in this study include Chat GPT and Llama, which have undergone extensive research and are primarily trained on English-language corpora, as well as ERNIE Bot, Kimi, Baichuan, Chat GLM, and Yi-large, which have gained significant attention and are primarily trained on Chinese-language corpora. A detailed description of the tested models is provided in Table 1. To ensure consistency and reproducibility, all LLMs were tested with default parameters and in a zero-shot setting.

Zhong Yao, Liantan Duan, Shuo Xu, Lingyi Chi, Dongfang Sheng

JMIR Med Inform 2025;13:e69485