AI 中文总结
LineageRAG 针对现有 GraphRAG 未明确证据发现与源 grounding 关联的问题，构建带源 grounding 的证据谱系，在三个多跳问答数据集上较基线实现多项指标提升。
AI 中文摘要
基于图的检索增强生成（GraphRAG）可针对结构化语料库图上的多跳问题检索证据。现有 GraphRAG 方法未明确证据发现与源 grounding 之间的关联。我们提出 LineageRAG，它为每个查询衍生的证据需求构建一条证据谱系，当所选证据支持该需求时，用逐字源文本片段完成谱系。LineageRAG 首先初始化证据需求，接着通过语料库图上的需求条件检索扩展每条谱系，同时保留每个候选的关联需求。谱系完成利用该溯源信息选择补充段落，并在逐字源文本中 grounding 已支持的需求。在 HotpotQA、2WikiMultiHopQA 和 MuSiQue 上的实验表明，与领先的 GraphRAG 基线相比，LineageRAG 的 R@5、EM 和 F1 平均分别提升 3.51、5.96 和 5.22 个百分点。
英文摘要
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.
