mlsanityData to 7 Oct 2026

LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding

arXiv 2608.16004 ↗First posted 17 Aug 2026cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Graph-based Retrieval-Augmented Generation (GraphRAG) retrieves evidence for multi-hop questions over structured cor- pus graphs. Existing GraphRAG methods leave the connection between evidence discovery and source grounding implicit. We propose LineageRAG, which constructs one evidence lin- eage for each query-derived evidence demand and completes it with a verbatim source span when the selected evidence supports that demand. LineageRAG first initializes the evi- dence demands. It then expands each lineage through demand- conditioned retrieval over the corpus graph while retaining the demand associated with every candidate. Lineage completion uses this provenance to select complementary passages and grounds supported demands in verbatim source text. Experi- ments on HotpotQA, 2WikiMultiHopQA, and MuSiQue show that LineageRAG improves R@5, EM, and F1 by 3.51, 5.96, and 5.22 points on average over leading GraphRAG baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 23 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

13 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG12 Jan
  2. 2025AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs2 Nov
  3. 2025SUBQRAG: Sub-Question Driven Dynamic Graph RAG9 Oct
  4. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Paths25 Apr
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 8

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  4. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  5. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  6. 2025G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledgecited by 9
  7. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
  8. 2026Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrievalcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG
  2. 2026EvLink: Source-Grounded Evidence Linking for Graph RAG
  3. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
  4. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  5. 2026DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation
  6. 2026PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation
  7. 2026TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation
  8. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs