AI RESEARCH
CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
arXiv CS.AI
•
ArXi:2603.08321v1 Announce Type: new Large language models (LLMs) show significant potential for clinical decision (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification.