[2603.01252] Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation

Computer Science > Computation and Language arXiv:2603.01252 (cs) [Submitted on 1 Mar 2026] Title:Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation Authors:Liwen Sun, Xiang Yu, Ming Tan, Zhuohao Chen, Anqi Cheng, Ashutosh Joshi, Chenyan Xiong View a PDF of the paper titled Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation, by Liwen Sun and 6 other authors View PDF HTML (experimental) Abstract:Clinical diagnosis is time-consuming, requiring intensive interactions between patients and medical professionals. While large language models (LLMs) could ease the pre-diagnostic workload, their limited domain knowledge hinders effective medical question generation. We introduce a Knowledge Graph-augmented LLM with active in-context learning to generate relevant and important follow-up questions, KG-Followup, serving as a critical module for the pre-diagnostic assessment. The structured medical domain knowledge graph serves as a seamless patch-up to provide professional domain expertise upon which the LLM can reason. Experiments demonstrate that KG-Followup outperforms state-of-the-art methods by 5% - 8% on relevant benchmarks in recall. Comments: Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.01252 [cs.CL]   (or arXiv:2603.01252v1 [cs.CL] for this version)   https://doi.org/10.48550/arXiv.2603.01252 Focus to learn more arXiv-issued DOI via DataCite (pend...