arXiv 2510.035362026-08-25cs.CLcs.AI

GraphMed-LT：面向多轮医疗对话的具有潜在临床思维优化的患者特定图记忆

GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversations

School of Computing Science, University of Glasgow, UK（格拉斯哥大学计算机科学学院）；School of Natural and Computing Science, University of Aberdeen, UK（阿伯丁大学自然与计算科学学院）

Zhaohan Meng, Zaiqiao Meng, Siwei Liu, Hao Xu, Ke Yuan, Iadh Ounis

备注：: Accepted to EMNLP 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究针对多轮医疗对话中临床证据分散的问题，提出GraphMed-LT方法，通过患者特定图记忆及潜在临床思维优化，在多轮医疗QA任务上较基线实现显著提升。

摘要：

多轮医疗问答（QA）旨在模拟真实的临床诊断场景，即医生在多轮对话中收集患者信息。现有的多轮医疗对话系统已取得良好进展，但通常依赖累积的对话历史作为记忆，导致临床证据在多轮中分散。本文提出GraphMed-LT，一种面向多轮医疗对话的患者特定图记忆方法，带有潜在临床思维优化。GraphMed-LT从患者回复中提取患者特定的临床三元组，检索相关知识三元组，并将其组织为增量更新的图记忆。该图记忆被投影为图条件证据标记，并在可训练的医生智能体内部通过隐藏状态反馈进行优化，使智能体在提出后续问题或生成最终答案前更新其内部临床上下文。在三个多轮医疗QA基准上的实验表明，GraphMed-LT在多个大语言模型（LLM）骨干上始终优于现有的多轮医疗对话基线，比最强基线实现了高达6.3个百分点的绝对提升。进一步分析显示，GraphMed-LT提出更具可回答性的后续问题，且在各医学专科均能提供稳定增益。

英文摘要：

Multi-turn medical question answering (QA) aims to model realistic clinical diagnosis, where a doctor gathers patient information across multiple turns of conversation. Existing multi-turn medical conversation systems have shown promising progress, but they often rely on accumulated conversation histories as memory, leaving clinical evidence fragmented across turns. We propose GraphMed-LT, a patient-specific graph memory approach with latent clinical thought refinement for multi-turn medical conversations. GraphMed-LT extracts patient-specific clinical triplets from patient responses, retrieves relevant knowledge triplets, and organises them into an incrementally updated graph memory. The graph memory is projected into graph-conditioned evidence tokens and refined inside a trainable doctor agent through hidden-state feedback, enabling the agent to update its internal clinical context before asking follow-up questions or producing the final answer. Experiments on three multi-turn medical QA benchmarks show that GraphMed-LT consistently outperforms existing multi-turn medical conversation baselines across multiple LLM backbones, achieving up to a 6.3 percentage-point absolute improvement over the strongest baseline. Further analyses show that GraphMed-LT asks more answerable follow-up questions and provides consistent gains across medical specialties.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。