构建跨模态图文图谱，高效检索复杂文档答案
HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document
- 用整体视图构建概念级图谱，减少噪声干扰
- 检索效率提升，准确率在三数据集上领先
- 适合处理图文混排的长文档问答任务
复杂文档的问答需要模型从相距较远的文档区域和多种模态中检索并整合证据。多模态图RAG通过图结构组织文档证据，展现出良好前景。但现有方法常面临跨模态证据索引不可靠、图遍历开销大的问题。为此，我们提出HVM-GraphRAG，一种面向复杂文档的整体视图多模态图RAG框架。该框架利用整体视图指导图谱构建，降低噪声与冲突更新，建立概念级节点与多模态证据块之间的可靠索引。检索时，直接在紧凑的概念级图上搜索，并通过索引快速定位支持证据，避免对密集实体级图的昂贵遍历。获得检索证据后，进一步将块按模态分组，帮助回答模型更好地融合异构证据。在三个数据集上的实验表明，HVM-GraphRAG在多数评估设置下表现最佳，同时显著提升了在线检索效率，优于代表性图基基线。
原文摘要 · Abstract (English)
Question answering (QA) over complex documents requires models to retrieve and integrate evidence distributed across distant document regions and modalities. Multimodal GraphRAG provides a promising direction by organizing document evidence with graph structures. However, existing methods often suffer from unreliable cross-modal evidence indexing and expensive graph traversal. To address these issues, we propose HVM-GraphRAG, a holistic-view multimodal GraphRAG framework on complex document. HVM-GraphRAG uses a holistic view to guide graph construction, thereby reducing noisy and conflicting graph updates and building reliable indices between concept-level graph nodes and supporting multimodal chunks. During retrieval, HVM-GraphRAG searches over a compact concept-level graph and directly accesses supporting evidence through the constructed index, avoiding costly traversal over dense entity-level graphs. After obtaining the retrieved evidence, HVM-GraphRAG further reorganizes chunks into modality-specific groups, enabling the answering model to better integrate heterogeneous evidence. Experiments on three datasets show that HVM-GraphRAG achieves the best answer performance in most evaluated settings while substantially improving online retrieval efficiency over representative graph-based 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。