通过构建证据链实现精准溯源，提升多跳问答准确性
LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding
- 为每个问题需求构建证据链条，显式关联证据与来源
- 在三个数据集上平均提升准确率3.51点，最高达5.96点
- 适合需要可解释性推理的智能问答系统开发者
基于图的检索增强生成（GraphRAG）在结构化语料图上对多跳问题进行证据检索。现有方法未明确证据发现与来源溯源之间的关系。本文提出LineageRAG，为每个查询衍生的证据需求构建一条证据链条，并在所选证据支持该需求时，用原文片段完成溯源。LineageRAG首先初始化证据需求，然后在语料图上通过需求条件化检索扩展每条链条，同时保留与每个候选项关联的需求。链路补全利用这一来源信息选择互补段落，并将被支持的需求以原文形式锚定。在HotpotQA、2WikiMultiHopQA和MuSiQue上的实验表明，LineageRAG在平均R@5、EM和F1上分别比领先基线提升3.51、5.96和5.22点。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。