Lingdan: enhancing encoding of traditional Chinese medicine knowledge for clinical reasoning tasks with large language models

Rui Hua, Xin Dong, Yu Wei, Zixin Shu, Pengcheng Yang, Yunhui Hu, Shuiping Zhou, He Sun, Kaijing Yan, Xijun Yan, Kai Chang, Xiaodong Li, Yuning Bai, Runshun Zhang, Wenjia Wang, Xuezhong Zhou

Abstract: The recent surge in large language models (LLMs) across various fields has yet to be fully realized in traditional Chinese medicine (TCM). This study aims to bridge this gap by developing a large language model tailored to TCM knowledge, enhancing its performance and accuracy in clinical reasoning tasks such as diagnosis, treatment, and prescription recommendations.