arXiv cs.AI· Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang·· 3 天前AI 评分22
基于分层多模态记忆的复杂长文档标题层级重建
Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
AI 导读
针对 VLM 逐页解析长文档时标题层级缺乏文档级一致性的问题，研究者提出一种基于 VLM 的框架，通过分层多模态记忆增量重建标题层级，该记忆按锚点保留此前处理页面的紧凑子集，并选取每层最新节点供模型观察各层级标题的视觉、文本与布局模式。
正文 · 原文
Abstract:Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models indicate heading levels using different numbers of preceding ``\#'' symbols, page-by-page prediction often lacks document-level consistency. In practice, input-resolution and context-length constraints make it infeasible for a VLM to jointly process all page images in documents containing tens or hundreds of pages. To address this limitation, we propose a VLM-based framework that incrementally reconstructs heading hierarchies with a \emph{level-wise multimodal memory}. The memory retains a compact subset of all previously processed pages, selected by anchors. Our framework supports flexible anchor selection, and in this work we select the most recent node at each level, allowing the VLM to observe the visual, textual, and layout patterns of headings at every level. For comprehensive evaluation, we also introduce the Complex and Long Document Heading Hierarchy Reconstruction Benchmark (CLDoc-HHRBench), comprising 250 documents and 11,212 pages with expert-verified annotations. Experiments on CLDoc-HHRBench and three existing benchmarks demonstrate the effectiveness of our method.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18238 [cs.CV] |
| (or arXiv:2610.18238v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18238 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qian Chen [view email]
[v1]
Tue, 13 Oct 2026 12:06:28 UTC (1,001 KB)
来源：arXiv cs.AI · arxiv.org