用知识图谱增强大模型，自动生成专业级问诊问题。
Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation
- 结合知识图谱与大模型，动态补充医学专业知识
- 在召回率上比现有方法提升5%至8%
- 适合医疗AI辅助问诊系统研发者使用
临床诊断耗时长，需患者与医生频繁互动。尽管大语言模型（LLMs）可减轻初步诊断负担，但其领域知识有限，制约了有效问诊问题的生成。我们提出一种融合知识图谱的主动上下文学习大模型——KG-Followup，用于生成相关且重要的随访问题，作为初步诊断评估的关键模块。结构化的医学知识图谱无缝补足了领域专长，使大模型能够基于此进行推理。实验表明，KG-Followup 在相关基准上的召回率优于当前最优方法5%至8%。
原文摘要 · Abstract (English)
Clinical diagnosis is time-consuming, requiring intensive interactions between patients and medical professionals. While large language models (LLMs) could ease the pre-diagnostic workload, their limited domain knowledge hinders effective medical question generation. We introduce a Knowledge Graph-augmented LLM with active in-context learning to generate relevant and important follow-up questions, KG-Followup, serving as a critical module for the pre-diagnostic assessment. The structured medical domain knowledge graph serves as a seamless patch-up to provide professional domain expertise upon which the LLM can reason. Experiments demonstrate that KG-Followup outperforms state-of-the-art methods by 5% - 8% on relevant benchmarks in recall.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。