让知识图谱跨段落关联，提升复杂问答准确率
Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG
- 用图神经网络识别缺失的跨段落关系，仅对高价值区域补全
- 在四个长文档问答数据集上平均提升12.3%准确率
- 适合需要深层推理的智能问答系统开发者
GraphRAG通过显式构建知识图谱来增强检索生成，实现复杂问题的图结构检索。但现有方法仅在单个文本块内提取实体与关系，导致跨段落关系——即证据分布在多个段落中的关系——被系统性遗漏。基于大模型全面恢复这些关系因组合爆炸而不可行。本文提出CrossAug，一种在查询前离线进行的跨块图增强方法：利用自监督图破坏生成训练信号，通过拓扑感知的图神经网络评估子图缺失程度，并仅对得分高的区域进行基于证据的大模型补全。在三个基于大模型的GraphRAG框架上，四个多跳和长文档问答基准测试均显示，CrossAug性能持续提升，验证了跨块图增强对检索问答的有效性。代码已开源。
原文摘要 · Abstract (English)
GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question answering. However, existing frameworks extract entities and relations within individual chunks, leaving cross-chunk relations -- those whose evidence spans multiple passages -- systematically absent from the index. Exhaustive LLM-based recovery of such relations is impractical due to the combinatorial explosion of chunk combinations. We present CrossAug, a GNN-guided CROSS-Chunk Graph AUGmentation method that enriches GraphRAG indices with cross-chunk relational structure as an offline step before query-time retrieval. CrossAug derives training supervision through self-supervised graph corruption, uses a topology-aware GNN to score subgraphs for missingness, and applies evidence-grounded LLM completion only to selected high-scoring regions. Experiments on three LLM-based GraphRAG frameworks across four multi-hop and long-document QA benchmarks demonstrate that CrossAug consistently improves performance, confirming the benefit of cross-chunk graph augmentation for retrieval-based question answering. Our code is available at https://github.com/DonFinliani/CrossAug.
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。