Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
This work addresses the need for more accurate and personalized medical dialogue systems for patients, representing an incremental improvement over existing methods.
The paper tackled the problem of medical dialogue systems struggling with relevant knowledge identification and personalized response generation by proposing MedRef, which improved generation quality and medical entity accuracy on benchmarks like MedDG and KaMed.
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.