mlsanityData to 14 Oct 2026

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

arXiv 2508.07493 ↗First posted 10 Aug 2025cs.CVcited by 14

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document retrieval or only consider multilingual question-answering on a single-page image. To bridge this gap, we introduce VisR-Bench, a multilingual benchmark designed for question-driven multimodal retrieval in long documents. Our benchmark comprises over 35K high-quality QA pairs across 1.2K documents, enabling fine-grained evaluation of multimodal retrieval. VisR-Bench spans sixteen languages with three question types (figures, text, and tables), offering diverse linguistic and question coverage. Unlike prior datasets, we include queries without explicit answers, preventing models from relying on superficial keyword matching. We evaluate various retrieval models, including text-based methods, multimodal encoders, and MLLMs, providing insights into their strengths and limitations. Our results show that while MLLMs significantly outperform text-based and multimodal encoder models, they still struggle with structured tables and low-resource languages, highlighting key challenges in multilingual visual retrieval.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 39 of its 46 references that are in the map. First posted on arXiv 10 Aug 2025.

Builds on

39 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents14 Oct

Other references · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Mistral 7Bcited by 3,164
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  7. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  9. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  10. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  11. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  12. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
26 more
  1. 2021InfographicVQAcited by 437
  2. 2019Scene Text Visual Question Answeringcited by 331
  3. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  4. 2024VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Taskscited by 228
  5. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 207
  6. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 183
  7. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 179
  8. 2024Building and better understanding vision-language models: insights and future directionscited by 173
  9. 2021TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene textcited by 171
  10. 2024GME: Improving Universal Multimodal Retrieval by Multimodal LLMscited by 170
  11. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 151
  12. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 135
  13. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmarkcited by 120
  14. 2024Unifying Multimodal Retrieval via Document Screenshot Embeddingcited by 110
  15. 2022Hierarchical multimodal transformers for Multi-Page DocVQAcited by 105
  16. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directionscited by 68
  17. 2024Needle In A Multimodal Haystackcited by 58
  18. 2025MMDocIR: Benchmarking Multimodal Retrieval for Long Documentscited by 43
  19. 2024M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Frameworkcited by 36
  20. 2024SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understandingcited by 25
  21. 2024SciMMIR: Benchmarking Scientific Multi-modal Information Retrievalcited by 23
  22. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  23. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  24. 2025Towards Visual Text Grounding of Multimodal Large Language Modelcited by 18
  25. 2024MMR: Evaluating Reading Ability of Large Multimodal Modelscited by 6
  26. 2025CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 10.

14 papers.

Sort:

By area:

  1. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  2. 2026KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMscited by 5
  3. 2025Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracycited by 4
  4. 2025SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documentscited by 4
  5. 2026DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agentscited by 3
  6. 2025Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Surveycited by 2
  7. 2026MINER: Mining Multimodal Internal Representation for Efficient Retrievalcited by 2
  8. 2025V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questionscited by 0
  9. 2026Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAGcited by 0
  10. 2026When AI Navigates the Fog of Warcited by 0
  11. 2026DISCO: Document Intelligence Suite for COmparative Evaluationcited by 0
  12. 2026UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewardscited by 0
2 more
  1. 2026CMDR: Contextual Multimodal Document Retrievalcited by 0
  2. 2026VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
  2. 2025Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
  3. 2024Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
  4. 2026SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
  5. 2026Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation
  6. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text
  7. 2025Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
  8. 2026Multimodal Graph RAG for Long-range Visually Rich Document Understanding