M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models

• URL: http://arxiv.org/abs/2605.18774v1
• Date: Fri, 17 Apr 2026 05:33:45 GMT
• Title: M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
• Abstract summary: We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree.<n>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.
• Score: 20.44093242908907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Hierarchical Evidence-Driven Reasoning for Long Document Understanding [95.51688464037096]
  We introduce HIEVI-RAG, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding.<n>Our framework significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
  arXiv  Detail & Related papers  (2026-07-06T03:08:28Z)
• Improving Long-Context Retrieval with Multi-Prefix Embedding [64.08968715893504]
  Multi-Prefix Embedding partitions a document into chunks separated by EOS tokens, encodes the full sequence in a single causal forward pass, and extracts one embedding at each prefix boundary.<n>MPE retains cross-chunk context, enables chunk-level MaxSim matching, and trains with only document-level relevance labels.
  arXiv  Detail & Related papers  (2026-06-22T17:31:02Z)
• MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing [34.19535115746437]
  MinerU-Popo is a lightweight framework for POst-Processing OCR outputs.<n>It decomposes the problem into four focused subtasks: text truncation recovery, table truncation recovery, title hierarchy, and image-text association.<n>It improves titlehierarchy TEDS by at least 20% across all five tested OCR models.
  arXiv  Detail & Related papers  (2026-05-24T10:00:28Z)
• MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing [74.84107522458798]
  MPDocBench-Parse is a benchmark for multi-page document parsing in real-world applications.<n>It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles.
  arXiv  Detail & Related papers  (2026-05-21T07:36:41Z)
• Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation [3.338186852016847]
  $$-RAG is a tree-RAG framework with two key components.<n>It supports diverse tasks from token-level question answering to document-level summarization.<n>It outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score.
  arXiv  Detail & Related papers  (2026-05-01T09:06:23Z)
• Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets [7.102370558887478]
  We present SLIDERS, a framework for question answering over long document collections through structured reasoning.<n> SLIDERS extracts salient information into a relational database, enabling scalable reasoning over persistent structured state.<n>It outperforms all baselines on three existing long-context benchmarks.
  arXiv  Detail & Related papers  (2026-04-24T07:16:44Z)
• LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding [23.227000200423458]
  We propose layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from page-level to block-level retrieval.<n>With block-level late retrieval, LFRAG enables precise query-content alignment and reduces irrelevant content for downstream generation.<n>Experiments on LFDocQA demonstrate that LFRAG achieves state-of-the-art performance on retrieval tasks, outperforms the best baseline by 7.20% in answer accuracy, and reduces token consumption by 73.07% in generation tasks.
  arXiv  Detail & Related papers  (2026-04-18T05:04:49Z)
• MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents [30.113467423647865]
  RAG-based QA has emerged as a powerful method for processing long industrial documents.<n>We introduce MultiDocFusion, a multimodal chunking pipeline that integrates vision-based document parsing, OCR, text extraction and reconstruction.<n>Experiments demonstrate that MultiDocFusion improves retrieval precision by 8-15% and ANLS QA scores by 2-3% compared to baselines.
  arXiv  Detail & Related papers  (2026-04-14T06:40:22Z)
• SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation [0.0]
  We introduce SPD-RAG, a hierarchical multi-agent framework for exhaustive cross-document question answering.<n>Each document is processed by a dedicated document-level agent operating only on its own content, enabling focused retrieval.<n>SPD-RAG achieves an Avg Score of 58.1 (GPT-5 evaluation), outperforming Normal RAG (33.0) and Agentic RAG (32.8) while using only 38% of the API cost of a full-context baseline (68.0)
  arXiv  Detail & Related papers  (2026-03-09T12:46:32Z)
• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation [22.803751188961865]
  We argue retrieval should move beyond similarity matching and instead operate over latent components.<n>We propose xMemory, which builds a hierarchy of intact units and maintains a searchable high-level node organisation.
  arXiv  Detail & Related papers  (2026-02-02T12:04:58Z)
• ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models [107.86069298500855]
  ToM is a novel Tree-oriented MapReduce framework for long-context reasoning.<n>We show that ToM significantly outperforms existing divide-and-conquer frameworks and retrieval-augmented generation methods.
  arXiv  Detail & Related papers  (2025-11-01T10:43:58Z)
• Docopilot: Improving Multimodal Models for Document-Level Understanding [87.60020625241178]
  We present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents.<n>This dataset includes diverse document structures, extensive cross-page dependencies, and real question-answer pairs derived from the original documents.<n>Building on the dataset, we develop a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
  arXiv  Detail & Related papers  (2025-07-19T16:03:34Z)
• Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval [68.71038700559195]
  Chain of Retrieval(COR) is a novel iterative framework for full-paper retrieval.<n>We present SCIBENCH, a benchmark providing both complete and segmented contexts of full papers for queries and candidates.
  arXiv  Detail & Related papers  (2025-07-14T08:41:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.