Saved in:
Bibliographic Details
Main Authors: Sun, Hongda, Peng, Jiaren, Yang, Wenzhong, He, Liang, Du, Bo, Yan, Rui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10877
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909647096512512
author Sun, Hongda
Peng, Jiaren
Yang, Wenzhong
He, Liang
Du, Bo
Yan, Rui
author_facet Sun, Hongda
Peng, Jiaren
Yang, Wenzhong
He, Liang
Du, Bo
Yan, Rui
contents Medical dialogue systems (MDS) have emerged as crucial online platforms for enabling multi-turn, context-aware conversations with patients. However, existing MDS often struggle to (1) identify relevant medical knowledge and (2) generate personalized, medically accurate responses. To address these challenges, we propose MedRef, a novel MDS that incorporates knowledge refining and dynamic prompt adjustment. First, we employ a knowledge refining mechanism to filter out irrelevant medical data, improving predictions of critical medical entities in responses. Additionally, we design a comprehensive prompt structure that incorporates historical details and evident details. To enable real-time adaptability to diverse patient conditions, we implement two key modules, Triplet Filter and Demo Selector, providing appropriate knowledge and demonstrations equipped in the system prompt. Extensive experiments on MedDG and KaMed benchmarks show that MedRef outperforms state-of-the-art baselines in both generation quality and medical entity accuracy, underscoring its effectiveness and reliability for real-world healthcare applications.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
Sun, Hongda
Peng, Jiaren
Yang, Wenzhong
He, Liang
Du, Bo
Yan, Rui
Computation and Language
Medical dialogue systems (MDS) have emerged as crucial online platforms for enabling multi-turn, context-aware conversations with patients. However, existing MDS often struggle to (1) identify relevant medical knowledge and (2) generate personalized, medically accurate responses. To address these challenges, we propose MedRef, a novel MDS that incorporates knowledge refining and dynamic prompt adjustment. First, we employ a knowledge refining mechanism to filter out irrelevant medical data, improving predictions of critical medical entities in responses. Additionally, we design a comprehensive prompt structure that incorporates historical details and evident details. To enable real-time adaptability to diverse patient conditions, we implement two key modules, Triplet Filter and Demo Selector, providing appropriate knowledge and demonstrations equipped in the system prompt. Extensive experiments on MedDG and KaMed benchmarks show that MedRef outperforms state-of-the-art baselines in both generation quality and medical entity accuracy, underscoring its effectiveness and reliability for real-world healthcare applications.
title Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
topic Computation and Language
url https://arxiv.org/abs/2506.10877