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

arXiv: https://arxiv.org/abs/2508.07493 · HTML: https://mlsanity.com/paper/2508.07493/

## 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.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://mlsanity.com/paper/2410.05160/) (2024)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)
- [Unifying Multimodal Retrieval via Document Screenshot Embedding](https://mlsanity.com/paper/2406.11251/) (2024)
- [Hierarchical multimodal transformers for Multi-Page DocVQA](https://mlsanity.com/paper/2212.05935/) (2022)
- [Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions](https://mlsanity.com/paper/2404.07214/) (2024)
- [Needle In A Multimodal Haystack](https://mlsanity.com/paper/2406.07230/) (2024)

## Built on by (most cited first, 14 of 14)

- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs](https://mlsanity.com/paper/2602.05929/) (2026)
- [Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy](https://mlsanity.com/paper/2510.22215/) (2025)
- [SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents](https://mlsanity.com/paper/2511.04910/) (2025)
- [DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents](https://mlsanity.com/paper/2606.26122/) (2026)
- [Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey](https://mlsanity.com/paper/2601.03262/) (2025)
- [MINER: Mining Multimodal Internal Representation for Efficient Retrieval](https://mlsanity.com/paper/2605.06460/) (2026)
- [V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions](https://mlsanity.com/paper/2512.11995/) (2025)
- [Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG](https://mlsanity.com/paper/2603.04238/) (2026)
- [When AI Navigates the Fog of War](https://mlsanity.com/paper/2603.16642/) (2026)
- [DISCO: Document Intelligence Suite for COmparative Evaluation](https://mlsanity.com/paper/2603.23511/) (2026)
- [UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards](https://mlsanity.com/paper/2604.14967/) (2026)
- [CMDR: Contextual Multimodal Document Retrieval](https://mlsanity.com/paper/2607.05927/) (2026)
- [VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval](https://mlsanity.com/paper/2610.17057/) (2026)

## 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.