EvLink: Source-Grounded Evidence Linking for Graph RAG
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Graph-based Retrieval-Augmented Generation (GraphRAG) supports multi-hop reasoning by organizing corpora into structured graphs. However, graph reachability often captures semantic association rather than evidence support, so a reachable passage may still fail to justify a required cross-passage transition. We propose EvLink, an evidence-linking retriever that preserves passages as retrievable evidence units and builds evidence-supported transitions between them. EvLink constructs two types of reliable links: relation-grounded evidence links justified by explicit source relations, and endpoint-alignment links serving as sourcebounded fallbacks. For retrieval, we introduce a two-stage retrieval strategy. First, bounded breadth-first search over source-grounded evidence links recovers bridge passages missed by similarity-based methods. Then, evidenceneed mining with noisy-OR coverage refinement selects a compact, non-redundant evidence set satisfying distinct question facets. Experiments on three multi-hop and two simple QA benchmarks show EvLink consistently outperforms leading GraphRAG baselines with average gains of 2.4 R@5, 1.9 EM, and 2.4 F1
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 15 of its 28 references that are in the map. First posted on arXiv 31 Aug 2026.
Builds on
15 of 28 references.
References · 15
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
- 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
- 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
- 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
- 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 61
- 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
- 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 23
3 more
- 2026SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answeringcited by 6
- 2026Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAGcited by 6
- 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
- 2026LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding
- 2026HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
- 2026PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation
- 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
- 2026STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation
- 2026Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
- 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs