mlsanityData to 7 Oct 2026

LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

arXiv 2202.13669 ↗First posted 28 Feb 2022cs.CLcited by 107

Not on the map. Why?

Abstract (arXiv)

Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However, most existing related models can only deal with the document data of specific language(s) (typically English) included in the pre-training collection, which is extremely limited. To address this issue, we propose a simple yet effective Language-independent Layout Transformer (LiLT) for structured document understanding. LiLT can be pre-trained on the structured documents of a single language and then directly fine-tuned on other languages with the corresponding off-the-shelf monolingual/multilingual pre-trained textual models. Experimental results on eight languages have shown that LiLT can achieve competitive or even superior performance on diverse widely-used downstream benchmarks, which enables language-independent benefit from the pre-training of document layout structure. Code and model are publicly available at https://github.com/jpWang/LiLT.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). Builds on 38 of its 45 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

38 of 45 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016Layer Normalizationcited by 5,579
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  9. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  10. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
  11. 2016Neural Architectures for Named Entity Recognitioncited by 548
  12. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 406
26 more
  1. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 345
  2. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
  3. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  4. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  5. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 212
  6. 2020UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Trainingcited by 204
  7. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  8. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  9. 2021LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understandingcited by 103
  10. 2018Chargrid: Towards Understanding 2D Documentscited by 100
  11. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  12. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91
  13. 2021StrucTexT: Structured Text Understanding with Multi-Modal Transformerscited by 90
  14. 2019Graph Convolution for Multimodal Information Extraction from Visually Rich Documentscited by 88
  15. 2020PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networkscited by 70
  16. 2021Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solutioncited by 64
  17. 2019BERTgrid: Contextualized Embedding for 2D Document Representation and Understandingcited by 63
  18. 2020TRIE: End-to-End Text Reading and Information Extraction for Document Understandingcited by 61
  19. 2018GraphIE: A Graph-Based Framework for Information Extractioncited by 45
  20. 2018Extracting Scientific Figures with Distantly Supervised Neural Networkscited by 36
  21. 2021ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documentscited by 29
  22. 2017Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classificationcited by 22
  23. 2018Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networkscited by 20
  24. 2021MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extractioncited by 18
  25. 2019Modular Multimodal Architecture for Document Classificationcited by 15
  26. 2021Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequencescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 37; 2024: 27; 2025: 17; 2026: 14.

107 papers.

Sort:

By area:

  1. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  2. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 159
  3. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 158
  4. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  5. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 95
  6. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understandingcited by 94
  7. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  8. 2023DocFormerv2: Local Features for Document Understandingcited by 46
  9. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
  10. 2023GeoLayoutLM: Geometric Pre-training for Visual Information Extractioncited by 40
  11. 2023ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extractioncited by 38
  12. 2022VRDU: A Benchmark for Visually-rich Document Understandingcited by 35
38 more
  1. 2024DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimmingcited by 35
  2. 2022Multimodal Pre-training Based on Graph Attention Network for Document Understandingcited by 23
  3. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
  4. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  5. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  6. 2022Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understandingcited by 20
  7. 2023Modeling Entities as Semantic Points for Visual Information Extraction in the Wildcited by 20
  8. 2023FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extractioncited by 20
  9. 2023DocTr: Document Transformer for Structured Information Extraction in Documentscited by 18
  10. 2023LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understandingcited by 17
  11. 2022Evaluating Out-of-Distribution Performance on Document Image Classifierscited by 16
  12. 2022VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classificationcited by 14
  13. 2022XDoc: Unified Pre-training for Cross-Format Document Understandingcited by 12
  14. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 12
  15. 2024Visually Guided Generative Text-Layout Pre-training for Document Intelligencecited by 12
  16. 2024Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understandingcited by 12
  17. 2023ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretrainingcited by 11
  18. 2023A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Imagescited by 9
  19. 2022Understanding Long Documents with Different Position-Aware Attentionscited by 7
  20. 2024PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answeringcited by 7
  21. 2023Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Modelscited by 6
  22. 2024Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Reviewcited by 6
  23. 2024SAIL: Sample-Centric In-Context Learning for Document Information Extractioncited by 6
  24. 2023Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentationcited by 5
  25. 2023On Evaluation of Document Classification using RVL-CDIPcited by 5
  26. 2024TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Modelcited by 5
  27. 2024XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parsercited by 5
  28. 2024Large Language Models for Page Stream Segmentationcited by 5
  29. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  30. 2023Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQAcited by 4
  31. 2023Information Redundancy and Biases in Public Document Information Extraction Benchmarkscited by 4
  32. 2023DocumentNet: Bridging the Data Gap in Document Pre-Trainingcited by 4
  33. 2024SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extractioncited by 4
  34. 2024ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-trainingcited by 4
  35. 2026VAREX: A Benchmark for Multi-Modal Structured Extraction from Documentscited by 4
  36. 2022FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Informationcited by 3
  37. 2023A Multi-Modal Multilingual Benchmark for Document Image Classificationcited by 3
  38. 20243MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understandingcited by 3

50 most cited of 107 All 107 (JSON)