LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding
2026-08-17 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors introduce LineageRAG, a system that helps answer complex questions by tracing clear evidence paths in structured graphs. Unlike earlier methods that loosely connect evidence to its sources, LineageRAG builds detailed 'lineages' of supporting facts and links them directly to exact text from the source. It starts by identifying what evidence is needed, then retrieves and organizes supporting passages accordingly. Their tests on multiple question-answering datasets show that LineageRAG finds more correct answers and better matches the source material than previous methods.
Graph-based RetrievalRetrieval-Augmented GenerationMulti-hop Question AnsweringEvidence LineageCorpus GraphSource GroundingHotpotQA2WikiMultiHopQAMuSiQuePassage Retrieval
Authors
Linyao Zheng, Xuhang Shi, Zhifang Mao, Sai Zhou, Shuaixian An, Xiuquan Hou, Jinze Li
Abstract
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.