International Journal of Education

This study focuses on the application of large language models (LLMs) in the evaluation of TCM English speech courses, exploring their significance in enhancing teaching quality and promoting the international dissemination of traditional Chinese medicine (TCM) culture. By establishing five core roles—“Peer Assessment Facilitator,” “Speech Logic Analyst,” “Language Accuracy Checker,” “Cross-Cultural Expression Evaluator,”and “Personalized Feedback Generator”—the research deeply integrates LLMs into the course evaluation system. Findings indicate that LLMs can enhance the objectivity of peer assessment by generating standardized evaluation frameworks; optimize speech logic structures through semantic analysis; ensure the accuracy of TCM English terminology by relying on authoritative corpora; improve the adaptability of cultural expression based on cross-cultural corpus learning; and deliver personalized feedback by integrating multi-dimensional data. This research provides both theoretical support and practical pathways for the intelligent transformation of TCM English teaching evaluation, effectively advancing the professional development of talent cultivation for international TCM cultural dissemination.

AI empowerment; TCM English speech courses; Multidimensional evaluation