Co-MedGraphRAG: A Collaborative Large–Small Model Medical Question-Answering Framework Enhanced by Knowledge Graph Reasoning
Information · 02.03.2026 · 17 (3) · 247
DOI: 10.3390/info17030247 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 02.03.2026. Verfasst von Sizhe Chen und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Large language models (LLMs) have demonstrated significant capabilities in natural language processing (NLP), but they often encounter challenges in the medical domain. This can result in insufficient alignment between generated answers and user intent, as well as factual deviations. To address these issues, we propose Co-MedGraphRAG, a novel framework combining knowledge graph reasoning with large–small model collaboration, aimed at improving the structural grounding and interpretability of medical responses. The framework operates through a multi-stage collaborative mechanism to augment question answering. First, a large language model constructs a question-specific knowledge graph (KG) containing pending entities (denoted as “none”) to explicitly define known and unknown variables. Subsequently, a hybrid reasoning strategy is employed to populate the pending entities, thereby completing the question-specific knowledge graph. Finally, this graph serves as critical structured evidence, combined with the original question, to augment the large language model in generating the final answer, implemented using Qwen2.5-7B and GLM4-9B in this paper. To evaluate the generated answers, we introduce a larger-parameter LLM(GPT-4o) to assess performance across five dimensions and compute an overall score. Experiments on three medical datasets demonstrate that Co-MedGraphRAG achieves consistent improvements in relevance, practicality, and structured knowledge support compared with mainstream Retrieval-Augmented Generation (RAG) frameworks. This work serves as a reference for researchers and developers designing medical question-answering frameworks and exploring decision-support applications.
Förderung
- Natural Science Foundation of Shandong Province
- National Natural Science Foundation of China
Zitieren
APA
Chen, S., & Chen, T. (2026). Co-MedGraphRAG: A Collaborative Large–Small Model Medical Question-Answering Framework Enhanced by Knowledge Graph Reasoning. Information, 17(3), 247. https://doi.org/10.3390/info17030247
Vancouver
Chen S, Chen T. Co-MedGraphRAG: A Collaborative Large–Small Model Medical Question-Answering Framework Enhanced by Knowledge Graph Reasoning. Information. 2026;17(3):247. doi:10.3390/info17030247
BibTeX
@article{Chen2026,
author = {Chen, Sizhe and Chen, Tao},
title = {Co-MedGraphRAG: A Collaborative Large–Small Model Medical Question-Answering Framework Enhanced by Knowledge Graph Reasoning},
journal = {Information},
year = {2026},
volume = {17},
number = {3},
pages = {247},
doi = {10.3390/info17030247}
}
EUVIMED