Large language models (LLMs) are advancing in multimodal understanding and reasoning, accelerating medical model development. Traditional Chinese medicine (TCM) uses evidence from the four examinations to determine disease location and nature, differentiate syndromes and guide treatment. This diagnostic process constitutes a complete chain of reasoning.
Fu-TCM模型构建
We present Fu-TCM, a multimodal TCM LLM trained on data retained after cleaning and filtering an initial collection of approximately 7.12 million examples derived from classical texts, textbooks, medical images, clinical cases and publicly available datasets.
模型优化与评估
The model was further optimized using Bianzheng-Grounded Policy Optimization (BGPO), which explicitly targets syndrome differentiation through rewards for response format, intermediate TCM reasoning fields and final syndrome predictions.
实验结果
Fu-TCM-27B led all six benchmarks spanning TCM reasoning, text and vision, achieving a macro-average accuracy of 81.01% and surpassing the strongest reference model with complete results across all six benchmarks by 7.13 percentage points. Its largest margin was 11.90 points on Fu-bianzheng.
案例分析
Case-level analyses further showed a positive association between intermediate-field accuracy and final syndrome-selection accuracy in most evaluated models.
研究结论
These findings suggest that TCM syndrome differentiation may be computationally learnable and that structured reasoning supervision can improve performance across TCM tasks.