Jialun Zhong's paper on dialogue-based medication recommendation, titled "Graph-Augmented Knowledge Infusion for Dialogue-Based Medication Recommendation" has been accepted by APWeb-WAIM 2026.

Medication recommendations have become an important task in the healthcare domain, especially in measuring the accuracy and safety of medical dialogue systems (MDS). Different from the recommendation task based on electronic health records (EHRs), dialogue-based medication recommendations require research on the interaction between patients and doctors, which is crucial but not exist in EHRs. Recent advancements in large language models (LLM) have extended the medical dialogue domain. These LLMs can interpret patients' intent and provide suggestions including medication recommendations, but some challenges are still worth attention. During a multi-turn dialogue, LLMs may ignore the fine-grained medical information or connections across the dialogue turns. Besides, LLMs may generate non-factual responses when there is a lack of domain-specific knowledge. Furthermore, when integrating heterogeneous knowledge sources, LLMs struggle to explicitly deduce the underlying compound logic. To address these challenges, we propose a Graph-Augmented Knowledge Infusion (GAKI) framework for dialogue-based medication recommendation. It extracts medical concepts and corresponding states from dialogue to construct an explicitly patient-centric graph, which can describe the neglected but important information. Further, combined with external knowledge sources, GAKI can reason on the graph and generate queries for retrieving complex knowledge to reduce the non-factual responses. We evaluate GAKI on a dialogue-based medication recommendation dataset and further explore its potential in a more difficult scenario, dynamically diagnostic interviewing. Extensive experiments demonstrate its competitive performance when compared with strong baselines.