TCM-ED
收藏资源简介:
TCM-ED数据集是由华东师范大学上海教育人工智能研究所创建,专门为评估大型语言模型在传统中医学(TCM)领域的性能而设计。该数据集包含5,473个问题,源自中医执业考试(TCMLE),覆盖中医基础理论和临床实践的核心内容。数据集的构建过程严格遵循专家指导,确保问题的全面性和代表性。TCM-ED数据集的应用旨在解决中医领域中大型语言模型评估标准缺失的问题,通过提供客观、可靠的评估工具,推动中医研究的发展。
The TCM-ED dataset was developed by the Shanghai Institute of Educational Artificial Intelligence at East China Normal University, and is specifically designed to evaluate the performance of large language models in the field of Traditional Chinese Medicine (TCM). This dataset comprises 5,473 questions sourced from the Licensed Traditional Chinese Medicine Practitioner Examination (TCMLE), covering core contents of TCM basic theory and clinical practice. The construction of the dataset strictly follows expert guidance to ensure the comprehensiveness and representativeness of the included questions. The TCM-ED dataset aims to address the lack of evaluation standards for large language models in the TCM domain, and to advance TCM research by providing an objective and reliable assessment tool.




