M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
📰 ArXiv cs.AI
arXiv:2605.18774v1 Announce Type: cross 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
Full Article
Title: M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
Abstract:
arXiv:2605.18774v1 Announce Type: cross 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
Abstract:
arXiv:2605.18774v1 Announce Type: cross 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
DeepCamp AI