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:Man-Zong Huang, Chenyang Bu, Yi He, Xingrui Zhuo, Xin-Dong Wu
- 年份:2026
- Venue:AAAI Conference on Artificial Intelligence
- DOI:10.48550/arXiv.2601.07192
- arXiv:2601.07192
- S2 citationCount(当前快照):12
- 来源线索:https://doi.org/10.48550/arXiv.2601.07192
摘要(未核验)
Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG methods are constrained by a prevailing build-then-reason paradigm, which relies on a static, pre-constructed Knowledge Graph (KG). This paradigm faces two critical challenges. First, the KG's inherent incompleteness often breaks reasoning paths. Second, the graph’s low signal-to-noise ratio introduces distractor facts, presenting query-relevant but misleading knowledge that disrupts the reasoning process. To address these challenges, we argue for a reason-and-construct paradigm and propose Relink, a framework that dynamically builds a query-specific evidence graph. To tackle incompleteness, Relink instantiates required facts from a latent relation pool derived from the original text corpus, repairing broken paths on the fly. To handle misleading or distractor facts, Relink employs a unified, query-aware evaluation strategy that jointly considers candidates from both the KG and latent relations, selecting those most useful for answering the query rather than relying on their pre-existence. This empowers Relink to actively discard distractor facts and construct the most faithful and precise evidence path for each query. Extensive experiments on five Open-Domain Question Answering benchmarks show that Relink achieves significant average improvements of 5.4% in EM and 5.2% in F1 over leading GraphRAG baselines, demonstrating the superiority of our proposed framework.
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。