Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment

TL;DR

This paper introduces MedRef, a medical dialogue system that enhances response accuracy and personalization by refining medical knowledge and dynamically adjusting prompts based on patient context.

Contribution

The paper presents a novel knowledge refining mechanism and dynamic prompt adjustment modules for improved medical dialogue generation.

Findings

Outperforms state-of-the-art baselines in generation quality

Achieves higher medical entity accuracy

Demonstrates effectiveness on MedDG and KaMed benchmarks

Abstract

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.