resource · 2026
LLM-Driven Unsupervised Discovery of Semantic Decision Dimensions for Dynamic Scheduling and Intelligent Systems: A Traditional Chinese Medicine Case Study
Mathematics
LLM-Driven Unsupervised Discovery of Semantic Decision Dimensions for Dynamic Scheduling and Intelligent Systems: A Traditional Chinese Medicine Case Study is a resource in the TCM LLM catalog (Awesome-TCM-LLM), dated 2026. It is maintained alongside the GitHub list of Traditional Chinese Medicine large language models.
DeepSeek-V3.2 induced 458 raw labels from 12,163 traditional Chinese medicine herb records and 64,107 short sentences, merged into 22 semantic categories; Qwen3-Embedding-8B found average internal coherence above 60% for 19 concepts, and experts rated reasonableness 4.64 on a 1-to-5 scale.