mlsanityData to 7 Oct 2026

LayoutReader: Pre-training of Text and Layout for Reading Order Detection

arXiv 2108.11591 ↗First posted 26 Aug 2021cs.CLcited by 79

Not on the map. Why?

Abstract (arXiv)

Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. We will release the dataset and model at urlhttps://aka.ms/layoutreader.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

7 of 16 references.

References · 7

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  3. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  4. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  5. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  6. 2019TableBank: A Benchmark Dataset for Table Detection and Recognitioncited by 102
  7. 2018Extracting Scientific Figures with Distantly Supervised Neural Networkscited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 11; 2024: 16; 2025: 18; 2026: 23.

79 papers.

Sort:

By area:

  1. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  2. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 95
  3. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 84
  4. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  5. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  6. 2022XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understandingcited by 68
  7. 2022ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understandingcited by 67
  8. 2024OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automationcited by 66
  9. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  10. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 44
  11. 2023Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMscited by 25
  12. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
38 more
  1. 2023LANS: A Layout-Aware Neural Solver for Plane Geometry Problemcited by 23
  2. 2025OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Modelscited by 22
  3. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  4. 2022Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understandingcited by 20
  5. 2025Towards Visual Text Grounding of Multimodal Large Language Modelcited by 18
  6. 2023LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understandingcited by 17
  7. 2024READoc: A Unified Benchmark for Realistic Document Structured Extractioncited by 15
  8. 2024Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysiscited by 14
  9. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patternscited by 13
  10. 2022XDoc: Unified Pre-training for Cross-Format Document Understandingcited by 12
  11. 2024Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understandingcited by 12
  12. 2022Relational Representation Learning in Visually-Rich Documentscited by 11
  13. 2024DLAFormer: An End-to-End Transformer For Document Layout Analysiscited by 11
  14. 2022Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Frameworkcited by 10
  15. 2025SuperRAG: Beyond RAG with Layout-Aware Graph Modelingcited by 9
  16. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 9
  17. 2022Multimodal Tree Decoder for Table of Contents Extraction in Document Imagescited by 8
  18. 2023Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answeringcited by 7
  19. 2023WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Datacited by 7
  20. 2023Enhancing Visually-Rich Document Understanding via Layout Structure Modelingcited by 6
  21. 2024DocGraphLM: Documental Graph Language Model for Information Extractioncited by 6
  22. 2023Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentationcited by 5
  23. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  24. 2024SynthDoc: Bilingual Documents Synthesis for Visual Document Understandingcited by 4
  25. 2024ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-trainingcited by 4
  26. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  27. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 4
  28. 2022Contrastive Training Improves Zero-Shot Classification of Semi-structured Documentscited by 3
  29. 2024Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extractioncited by 3
  30. 2025UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysiscited by 3
  31. 2026Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategycited by 3
  32. 2023DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Readingcited by 2
  33. 2023On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrievalcited by 2
  34. 2024Reading Order Independent Metrics for Information Extraction in Handwritten Documentscited by 2
  35. 2025Class-Agnostic Region-of-Interest Matching in Document Imagescited by 2
  36. 2025DREAM: Document Reconstruction via End-to-end Autoregressive Modelcited by 2
  37. 2025PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Modelscited by 2
  38. 2026GutenOCR: A Grounded Vision-Language Front-End for Documentscited by 2

50 most cited of 79 All 79 (JSON)