# Document Collection Visual Question Answering

arXiv: https://arxiv.org/abs/2104.14336 · HTML: https://mlsanity.com/paper/2104.14336/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2021.

## Built on by (most cited first, 30 of 45)

- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [Hierarchical multimodal transformers for Multi-Page DocVQA](https://mlsanity.com/paper/2212.05935/) (2022)
- [Benchmarking and Improving Detail Image Caption](https://mlsanity.com/paper/2405.19092/) (2024)
- [A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram](https://mlsanity.com/paper/2302.11097/) (2023)
- [CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts](https://mlsanity.com/paper/2405.05949/) (2024)
- [Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark](https://mlsanity.com/paper/2407.13766/) (2024)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [OCR-IDL: OCR Annotations for Industry Document Library Dataset](https://mlsanity.com/paper/2202.12985/) (2022)
- [SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding](https://mlsanity.com/paper/2411.01106/) (2024)
- [u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model](https://mlsanity.com/paper/2311.05348/) (2023)
- [LANS: A Layout-Aware Neural Solver for Plane Geometry Problem](https://mlsanity.com/paper/2311.16476/) (2023)
- [MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding](https://mlsanity.com/paper/2407.04903/) (2024)
- [GRAM: Global Reasoning for Multi-Page VQA](https://mlsanity.com/paper/2401.03411/) (2024)
- [MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning](https://mlsanity.com/paper/2406.17770/) (2024)
- [Watching the News: Towards VideoQA Models that can Read](https://mlsanity.com/paper/2211.05588/) (2022)
- [Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment](https://mlsanity.com/paper/2405.17871/) (2024)
- [Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition](https://mlsanity.com/paper/2412.09501/) (2024)
- [ICDAR 2021 Competition on Document VisualQuestion Answering](https://mlsanity.com/paper/2111.05547/) (2021)
- [Privacy-Aware Document Visual Question Answering](https://mlsanity.com/paper/2312.10108/) (2023)
- [World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering](https://mlsanity.com/paper/2409.20424/) (2024)
- [Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram](https://mlsanity.com/paper/2407.07327/) (2024)
- [Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering](https://mlsanity.com/paper/2306.16713/) (2023)
- [ANLS* -- A Universal Document Processing Metric for Generative Large Language Models](https://mlsanity.com/paper/2402.03848/) (2024)
- [JDocQA: Japanese Document Question Answering Dataset for Generative Language Models](https://mlsanity.com/paper/2403.19454/) (2024)
- [LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer](https://mlsanity.com/paper/2412.13871/) (2024)
- [PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering](https://mlsanity.com/paper/2404.12720/) (2024)
- [Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition](https://mlsanity.com/paper/2503.12303/) (2025)
- [Vision-Speech Models: Teaching Speech Models to Converse about Images](https://mlsanity.com/paper/2503.15633/) (2025)

## Abstract (arXiv)

Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.