RagMedge:Dense Retrieval Augmented Medical Dialogue Generation Towards Personalized Medical Knowledge Grounded DiagnosisOA
To develop a medical generative system,current research has primarily focused on integrating medical knowledge into language models(LMs)through training them on medical corpora or incorporating external medical resources,such as knowledge graphs and terminologies.However,approaches rely on implicit knowledge integration from textual narratives or standardized knowledge sources(e.g.,Unified Medical Language System),making the acquired knowledge opaque and difficult to control during inference.This lack of transparency limits the traceability of knowledge accumulated from historical training data.To address these limitations,we propose constructing a personalized medical knowledge base that extracts discrete knowledge points from real doctor-patient dialogues and encodes them as semantically condensed vectors.Building on this,we introduce a novel dense retrieval-augmented medical dialogue generation framework,called RagMedge,which retrieves relevant knowledge embeddings conditioned on the input context and incorporates them into response generation.Experimental results demonstrate that RagMedge achieves state-of-the-art performance,highlighting the effectiveness of leveraging personalized medical knowledge for improved dialogue generation.
Bo Lyu;Chen Tang;Guo-Xin Yu;Na-Yu Liu;Yue Yu
Key Laboratory of Intelligent Information Processing of the Chinese Academy of Sciences,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China Pengcheng Laboratory,Shenzhen 518000,China University of Chinese Academy of Sciences,Beijing 100190,ChinaDepartment of Computer Science,The University of Manchester,Manchester M139PL,U.K.Pengcheng Laboratory,Shenzhen 518000,ChinaUniversity of Chinese Academy of Sciences,Beijing 100190,ChinaPengcheng Laboratory,Shenzhen 518000,China
信息技术与安全科学
retrieval augmented generationmedical dialogue generationnatural language generationdataset construction
《Journal of Computer Science & Technology》 2026 (3)
P.961-976,16
supported by the National Key R&D Program of China under Grant No.2022ZD0115301the Major Key Project of Pengcheng Laboratory under Grant No.PCL2025AS11the National Natural Science Foundation of China under Grant No.62406223.
评论