检索说明
- 查询:GraphRAG evidence retrieval
- 年份过滤:2025-
- 单查询上限:20
- 发现日期:2026-11-12
Semantic Scholar 候选元数据
- 作者:S. Mohammed, J. Fiaidhi, T. Sekar, K. Kushal, S. Shankar
- 年份:2025
- Venue:medRxiv
- DOI:10.1101/2025.05.03.25325604
- arXiv:未返回
- S2 citationCount(当前快照):2
- 来源线索:https://doi.org/10.1101/2025.05.03.25325604
摘要(未核验)
The integration of evidence-based reasoning with retrieval-augmented generation (GraphRAG) holds great promise for enhancing large language model (LLM) question-answering (QA) capabilities. This research proposes a GraphRAG frame- work that improves the interpretability and reliability of LLM- generated answers in the medical domain. Our approach con- structs a knowledge graph using Neo4j to represent UMLS medical entities and relationships, and complements it with a vector store of textbook embeddings for dense passage retrieval. The system is designed to combine symbolic reasoning and semantic search to produce more context-aware and evidence- grounded responses. As a proof of concept, we evaluate our system on United States Medical Licensing Examination (USMLE)- style questions, which require clinical reasoning across multiple domains. While overall answer accuracy remains comparable to that of an LLM only baseline, our system consistently out- performs in citation fidelity; providing richer, more traceable justifications by explicitly linking answers to graph paths and textbook passages. These findings suggest that even when correctness may vary, graph-informed retrieval improves transparency and auditability, which are critical for high-stakes domains like medicine. Our results motivate further refinement of hybrid GraphRAG systems to enhance both factual accuracy and clinical trustworthiness in QA applications.
转为正式文献前的核验清单
- [ ] 从论文、出版社、会议、ACL Anthology、OpenReview 或 arXiv 页面核对标题、作者、年份和版本。
- [ ] 核对 DOI、venue、正式链接和是否存在撤稿/版本变化。
- [ ] 阅读正文后补充方法、证据边界、结果和与现有研究的关系。
Semantic Scholar 记录用于发现候选,不是正式一手引文,也不支持对结果覆盖范围或研究质量的穷尽性判断。