Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.00216 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912983462969344 |
|---|---|
| author | Zhang, Jinning Song, Jie Tu, Wenhui Li, Zecheng Li, Jingxuan Li, Jin Liu, Xuan Sha, Taole Wei, Zichen Li, Yan |
| author_facet | Zhang, Jinning Song, Jie Tu, Wenhui Li, Zecheng Li, Jingxuan Li, Jin Liu, Xuan Sha, Taole Wei, Zichen Li, Yan |
| contents | Current medical retrieval-augmented generation (RAG) approaches overlook evidence-based medicine (EBM) principles, leading to two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present SR-RAG, an EBM-adapted GraphRAG framework that integrates the PICO framework into knowledge graph construction and retrieval, and proposes Bayesian Evidence Tier Reranking (BETR) to calibrate ranking scores by evidence grade without predefined weights. Validated in sports rehabilitation, we release a knowledge graph (357,844 nodes, 371,226 edges) and a benchmark of 1,637 QA pairs. SR-RAG achieves 0.812 evidence recall@10, 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy, substantially outperforming five baselines. Five expert clinicians rated the system 4.66--4.84 on a 5-point Likert scale, and system rankings are preserved on a human-verified gold subset (n=80). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00216 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark Zhang, Jinning Song, Jie Tu, Wenhui Li, Zecheng Li, Jingxuan Li, Jin Liu, Xuan Sha, Taole Wei, Zichen Li, Yan Computation and Language Current medical retrieval-augmented generation (RAG) approaches overlook evidence-based medicine (EBM) principles, leading to two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present SR-RAG, an EBM-adapted GraphRAG framework that integrates the PICO framework into knowledge graph construction and retrieval, and proposes Bayesian Evidence Tier Reranking (BETR) to calibrate ranking scores by evidence grade without predefined weights. Validated in sports rehabilitation, we release a knowledge graph (357,844 nodes, 371,226 edges) and a benchmark of 1,637 QA pairs. SR-RAG achieves 0.812 evidence recall@10, 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy, substantially outperforming five baselines. Five expert clinicians rated the system 4.66--4.84 on a 5-point Likert scale, and system rankings are preserved on a human-verified gold subset (n=80). |
| title | From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.00216 |