Summary of Biancang: a Traditional Chinese Medicine Large Language Model, by Sibo Wei et al.
BianCang: A Traditional Chinese Medicine Large Language Model
by Sibo Wei, Xueping Peng, Yi-fei Wang, Jiasheng Si, Weiyu Zhang, Wenpeng Lu, Xiaoming Wu, Yinglong Wang
First submitted to arxiv on: 17 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes BianCang, a large language model (LLM) specifically designed for traditional Chinese medicine (TCM). Current LLMs struggle with TCM diagnosis and syndrome differentiation due to differences between TCM and modern medical theory. To address this challenge, the authors develop a two-stage training process that injects domain-specific knowledge and aligns it through targeted stimulation. The model is trained on 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. Evaluations across 11 test sets involving 29 models and 4 tasks demonstrate the effectiveness of BianCang. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a special computer model called BianCang that can understand traditional Chinese medicine (TCM). TCM is very different from modern medicine, which makes it hard for computers to learn about it. The authors came up with a new way to teach the model, using a mix of old and new information. They used lots of texts and data to train the model, including records from hospitals and a special database that’s only available in China. The results show that BianCang is very good at understanding TCM and making diagnoses. |
Keywords
» Artificial intelligence » Large language model
