BianCang: A Traditional Chinese Medicine Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Sibo, Peng, Xueping, Wang, Yi-Fei, Shen, Tao, Si, Jiasheng, Zhang, Weiyu, Zhu, Fa, Vasilakos, Athanasios V., Lu, Wenpeng, Wu, Xiaoming, Wang, Yinglong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915523251404800
author Wei, Sibo
Peng, Xueping
Wang, Yi-Fei
Shen, Tao
Si, Jiasheng
Zhang, Weiyu
Zhu, Fa
Vasilakos, Athanasios V.
Lu, Wenpeng
Wu, Xiaoming
Wang, Yinglong
author_facet Wei, Sibo
Peng, Xueping
Wang, Yi-Fei
Shen, Tao
Si, Jiasheng
Zhang, Weiyu
Zhu, Fa
Vasilakos, Athanasios V.
Lu, Wenpeng
Wu, Xiaoming
Wang, Yinglong
contents The surge of large language models (LLMs) has driven significant progress in medical applications, including traditional Chinese medicine (TCM). However, current medical LLMs struggle with TCM diagnosis and syndrome differentiation due to substantial differences between TCM and modern medical theory, and the scarcity of specialized, high-quality corpora. To this end, in this paper we propose BianCang, a TCM-specific LLM, using a two-stage training process that first injects domain-specific knowledge and then aligns it through targeted stimulation to enhance diagnostic and differentiation capabilities. Specifically, we constructed pre-training corpora, instruction-aligned datasets based on real hospital records, and the ChP-TCM dataset derived from the Pharmacopoeia of the People's Republic of China. We compiled extensive TCM and medical corpora for continual pre-training and supervised fine-tuning, building a comprehensive dataset to refine the model's understanding of TCM. Evaluations across 11 test sets involving 31 models and 4 tasks demonstrate the effectiveness of BianCang, offering valuable insights for future research. Code, datasets, and models are available on https://github.com/QLU-NLP/BianCang.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11027
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BianCang: A Traditional Chinese Medicine Large Language Model
Wei, Sibo
Peng, Xueping
Wang, Yi-Fei
Shen, Tao
Si, Jiasheng
Zhang, Weiyu
Zhu, Fa
Vasilakos, Athanasios V.
Lu, Wenpeng
Wu, Xiaoming
Wang, Yinglong
Computation and Language
Artificial Intelligence
The surge of large language models (LLMs) has driven significant progress in medical applications, including traditional Chinese medicine (TCM). However, current medical LLMs struggle with TCM diagnosis and syndrome differentiation due to substantial differences between TCM and modern medical theory, and the scarcity of specialized, high-quality corpora. To this end, in this paper we propose BianCang, a TCM-specific LLM, using a two-stage training process that first injects domain-specific knowledge and then aligns it through targeted stimulation to enhance diagnostic and differentiation capabilities. Specifically, we constructed pre-training corpora, instruction-aligned datasets based on real hospital records, and the ChP-TCM dataset derived from the Pharmacopoeia of the People's Republic of China. We compiled extensive TCM and medical corpora for continual pre-training and supervised fine-tuning, building a comprehensive dataset to refine the model's understanding of TCM. Evaluations across 11 test sets involving 31 models and 4 tasks demonstrate the effectiveness of BianCang, offering valuable insights for future research. Code, datasets, and models are available on https://github.com/QLU-NLP/BianCang.
title BianCang: A Traditional Chinese Medicine Large Language Model
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.11027