Reproduce “Fu-TCM: a multimodal large language model that learns traditional Chinese medicine diagnostic reasoning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiahang Xie, Tong Jin, Lingfei Wu, Yaping You, Jie Huang, Yuanchang Jin, Weikang Gong, Wei Cheng and 4 more
Fu-TCM is a multimodal model for traditional Chinese medicine diagnosis that predicts a syndrome through explicit intermediate bianzheng fields. It is trained on domain data and with rewards for response format, syndrome prediction, and intermediate fields. Fu-TCM-27B ranked first on six benchmarks and achieved 81.01% macro-average accuracy, but this is benchmark evidence, not clinical validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.