用视觉语言模型重建文档层级关系，提升长篇多页文档的分块质量。
M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
- 先恢复文档块间的父子依赖关系，再基于树结构分块。
- 在DHP和语料级RAG基准上，检索nDCG提升1.1至15.3个百分点。
- 适合处理工业文档等复杂多模态长文档的智能分块任务。
在长篇多页工业文档中，检索增强生成（RAG）的效果高度依赖于分块边界是否符合文档真实结构。现有文本中心的分块方法和生成式层次解析器常遗漏跨页父子关系、图表与标题的绑定及边界线索，导致分块碎片化或冗余，降低检索与问答质量。我们提出M3DocDep，一种基于大视觉语言模型的流水线：首先通过SharedDet统一处理页面与OCR，利用边界感知的SoftROI池化提取多模态块嵌入，用双仿射头评分候选父子边，结合最小生成树（MST）约束解码全局有效依赖树，最终构建带章节路径与页码范围标注的树引导分块。在共享块评估协议下，M3DocDep在DHP基准上使STEDS提升28.5%至39.6%，检索nDCG提升1.1%至15.3%，语料级RAG上的问答ANLS提升4.5%至15.3%。结果表明，分块前先恢复文档依赖关系，能生成更连贯的检索单元。
原文摘要 · Abstract (English)
In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss cross-page parent-child relations, figure/table-caption bindings, and boundary cues, which leads to fragmented or redundant chunks and degrades both retrieval and answer quality. We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree. The pipeline uses SharedDet as a common DP+OCR preprocessing layer, extracts multimodal block embeddings with boundary-aware SoftROI pooling, scores candidate parent-child edges with a biaffine head, decodes a globally valid dependency tree with MST constraints, and builds tree-guided chunks annotated with section paths and page ranges. Under a shared-block evaluation protocol, M3DocDep improves STEDS by +28.5 to +39.6 percent on DHP benchmarks, retrieval nDCG by +1.1 to +15.3 percent, and QA ANLS by +4.5 to +15.3 percent on corpus-level RAG benchmarks. These results show that recovering document dependencies before chunking yields more coherent retrieval units for long, multi-page multimodal documents.
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。