多智能体LLM结合RAG优化甲亢入院记录
Quality optimization with low positive factual hallucination for the HPI in hyperthyroidism admission notes using multi agent LLM with RAG
精选理由
用多智能体加RAG写甲亢病历，能把事实幻觉压得很低，做医疗文本生成的可以看看。
本研究提出一种多智能体LLM结合RAG的方法，用于优化甲亢入院记录中的现病史。该方法在生成HPI时，将阳性事实幻觉率控制在较低水平。实验表明该多智能体架构在保证生成质量的同时，有效降低了RAG过程中的事实性错误。
原文 · npj Digital Medicine
Quality optimization with low positive factual hallucination for the HPI in hyperthyroidism admission notes using multi agent LLM with RAG
npj Digital Medicine, Published online: 07 October 2026; doi:10.1038/s41746-026-03321-x Quality optimization with low positive factual hallucination for the HPI in hyperthyroidism admission notes using multi agent LLM with RAG
