mlsanityData to 14 Oct 2026

PDFVQA: A New Dataset for Real-World VQA on PDF Documents

arXiv 2304.06447 ↗First posted 13 Apr 2023cs.CV cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

Document-based Visual Question Answering examines the document understanding of document images in conditions of natural language questions. We proposed a new document-based VQA dataset, PDF-VQA, to comprehensively examine the document understanding from various aspects, including document element recognition, document layout structural understanding as well as contextual understanding and key information extraction. Our PDF-VQA dataset extends the current scale of document understanding that limits on the single document page to the new scale that asks questions over the full document of multiple pages. We also propose a new graph-based VQA model that explicitly integrates the spatial and hierarchically structural relationships between different document elements to boost the document structural understanding. The performances are compared with several baselines over different question types and tasksfootnoteThe full dataset will be released after paper acceptance.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

28 of 35 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  3. 2015VQA: Visual Question Answeringcited by 2,506
  4. 2019Towards VQA Models That Can Readcited by 1,718
  5. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  6. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  7. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  8. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  9. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  10. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  11. 2021InfographicVQAcited by 437
  12. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
16 more
  1. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  2. 2018DVQA: Understanding Data Visualizations via Question Answeringcited by 340
  3. 2019Scene Text Visual Question Answeringcited by 331
  4. 2019PlotQA: Reasoning over Scientific Plotscited by 321
  5. 2017FigureQA: An Annotated Figure Dataset for Visual Reasoningcited by 319
  6. 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 256
  7. 2021VisualMRC: Machine Reading Comprehension on Document Imagescited by 151
  8. 2019Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQAcited by 107
  9. 2020On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answeringcited by 78
  10. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  11. 2019LEAF-QA: Locate, Encode & Attend for Figure Question Answeringcited by 54
  12. 2021VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relationscited by 40
  13. 2022Multimodal Pre-training Based on Graph Attention Network for Document Understandingcited by 24
  14. 2022V-Doc : Visual questions answers with Documentscited by 19
  15. 2022Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysiscited by 17
  16. 2021Visual FUDGE: Form Understanding via Dynamic Graph Editingcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 9; 2025: 6; 2026: 8.

28 papers.

Sort:

By area:

  1. 2024NVLM: Open Frontier-Class Multimodal LLMscited by 125
  2. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understandingcited by 111
  3. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 76
  4. 2025FineVision: Open Data Is All You Needcited by 53
  5. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysiscited by 40
  6. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  7. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunitiescited by 25
  8. 2024Deep Learning based Visually Rich Document Content Understanding: A Surveycited by 21
  9. 2024StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyondcited by 11
  10. 2024RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoningcited by 8
  11. 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
  12. 2024PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answeringcited by 7
16 more
  1. 2023MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answeringcited by 1
  2. 2024The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcriptscited by 1
  3. 2025LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receiptscited by 1
  4. 2025GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMscited by 1
  5. 2025MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Usecited by 1
  6. 2026Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Modelscited by 1
  7. 2026DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillationcited by 1
  8. 2023Workshop on Document Intelligence Understandingcited by 0
  9. 2023Jaeger: A Concatenation-Based Multi-Transformer VQA Modelcited by 0
  10. 2023Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selectioncited by 0
  11. 2025SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extractioncited by 0
  12. 2026VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understandingcited by 0
  13. 2026RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradationscited by 0
  14. 2026From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analyticscited by 0
  15. 2026Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystemscited by 0
  16. 2026Lightweight and Production-Ready PDF Visual Element Parsingcited by 0