Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing

• URL: http://arxiv.org/abs/2604.02692v1
• Date: Fri, 03 Apr 2026 03:36:36 GMT
• Title: Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
• Abstract summary: We introduce a lightweight structural refinement stage between a DETR-style detector and the interface to stabilize the interface.<n>Treating raw detector outputs as a compact hypothesis pool, the proposed module performs set-level reasoning over query features, semantic cues, box geometry, and visual evidence.<n>From a shared refined structural state, it jointly determines instance retention, refines box localization, and predicts input order before handoff.<n>Extensive experiments on public benchmarks show that our method consistently improves page-level layout quality.
• Score: 23.497081928689525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector output. Instead, they operate on a retained and serialized set of layout instances. However, on dense pages with overlapping regions and ambiguous boundaries, unstable layout hypotheses can make the retained instance set inconsistent with its parser input order, leading to severe downstream parsing errors. To address this issue, we introduce a lightweight structural refinement stage between a DETR-style detector and the parser to stabilize the parser interface. Treating raw detector outputs as a compact hypothesis pool, the proposed module performs set-level reasoning over query features, semantic cues, box geometry, and visual evidence. From a shared refined structural state, it jointly determines instance retention, refines box localization, and predicts parser input order before handoff. We further introduce retention-oriented supervision and a difficulty-aware ordering objective to better align the retained instance set and its order with the final parser input, especially on structurally complex pages. Extensive experiments on public benchmarks show that our method consistently improves page-level layout quality. When integrated into a standard end-to-end parsing pipeline, the stabilized parser interface also substantially reduces sequence mismatch, achieving a Reading Order Edit of 0.024 on OmniDocBench.

Related papers

• Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach [58.15427952222424]
  General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples.<n>We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.
  arXiv  Detail & Related papers  (2026-08-15T13:19:25Z)
• RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild [14.715243408844058]
  We present RT-Doc, a highly efficient end-to-end framework for document layout analysis.<n>The proposed model unifies classification, pixel-level segmentation, and geometric order reading order prediction for layout elements.<n> RT-Doc significantly improves full-document reconstruction quality, providing a scalable and practical foundation for real-world document intelligence systems.
  arXiv  Detail & Related papers  (2026-06-22T13:48:39Z)
• ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction [20.591821598269707]
  We propose ParseFixer, an agentic framework for backbone parsing and selective correction.<n>ParseFixer consists of two key modules: Full-Page Backbone Parsing (FBP) and Agentic Selective Correction (ASC)<n>By placing selective multimodal correction after open-source backbone parsing, ParseFixer improves the recovery of key document elements without rewriting reliable backbone predictions.
  arXiv  Detail & Related papers  (2026-06-10T11:55:18Z)
• Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing [53.41293908252118]
  We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level document parsing.<n>Dr. DocBench spans 52 BISAC domains and selects documents through failure-based sampling.<n>It contains 4,514 annotated pages from long documents averaging around 100 pages, with 65k high-quality annotations for layout, reading order, hierarchical relations, and domain-specific visual contents.<n>Our analysis reveals substantial failures across subjects, content types, and structural attributes, highlighting Dr. DocBench as a comprehensive testbed for diagnosing and advancing document intelligence.
  arXiv  Detail & Related papers  (2026-05-31T18:35:30Z)
• 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)
• Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation [19.889854990300595]
  Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions.<n>We present textbfChain of Evidence (CoE), a retriever-agnostic visual attribution framework.
  arXiv  Detail & Related papers  (2026-05-02T06:40:42Z)
• Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training [23.87978106727431]
  We propose a data-training co-design framework for robust end-to-end document parsing.<n>Our method achieves superior accuracy and robustness across both scanned/digital and real-world captured scenarios.
  arXiv  Detail & Related papers  (2026-03-25T03:19:09Z)
• Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding [102.88996030431662]
  We propose a training-free and highly efficient acceleration method for document parsing tasks.<n>Inspired by speculative decoding, we employ a lightweight document parsing pipeline as a draft model to predict batches of future tokens.<n>We demonstrate the effectiveness of our approach on the general-purpose OmniDocBench.
  arXiv  Detail & Related papers  (2026-02-13T14:22:10Z)
• SPIRE: Structure-Preserving Interpretable Retrieval of Evidence [0.09558392439655013]
  We present a structure-aware retrieval pipeline that operates over tree-structured documents.<n>We define a small set of document primitives--paths and path sets.<n>Global contextualization adds the non-local scaffolding needed to make a selection intelligible.<n>Local contextualization expands a seed selection within its structural neighborhood to obtain a compact, context-rich view.
  arXiv  Detail & Related papers  (2026-02-12T03:46:10Z)
• ROAP: A Reading-Order and Attention-Prior Pipeline for Optimizing Layout Transformers in Key Information Extraction [5.594845708011402]
  This paper presents ROAP, a lightweight and architecture-agnostic pipeline designed to optimize attention distributions in layout Transformers.<n> experiments on the FUNSD and CORD benchmarks demonstrate that ROAP consistently improves the performance of backbones.
  arXiv  Detail & Related papers  (2026-01-09T02:02:37Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing [46.14775667559124]
  layoutRL is an end-to-end reinforcement learning framework that trains models to be explicitly layout-aware.<n>We will publicly release our code and dataset to accelerate progress in robust document understanding.
  arXiv  Detail & Related papers  (2025-06-01T15:19:52Z)
• Multilevel Text Alignment with Cross-Document Attention [59.76351805607481]
  Existing alignment methods operate at a single, predefined level. We propose a new learning approach that equips previously established hierarchical attention encoders for representing documents with a cross-document attention component.
  arXiv  Detail & Related papers  (2020-10-03T02:52:28Z)

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.