# UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

arXiv: https://arxiv.org/abs/2510.03663 · HTML: https://mlsanity.com/paper/2510.03663/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (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)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [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)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [ColPali: Efficient Document Retrieval with Vision Language Models](https://mlsanity.com/paper/2407.01449/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [xGen-MM (BLIP-3): A Family of Open Large Multimodal Models](https://mlsanity.com/paper/2408.08872/) (2024)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [Unifying Multimodal Retrieval via Document Screenshot Embedding](https://mlsanity.com/paper/2406.11251/) (2024)
- [PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System](https://mlsanity.com/paper/2206.03001/) (2022)
- [Towards Complex Document Understanding By Discrete Reasoning](https://mlsanity.com/paper/2207.11871/) (2022)
- [VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2505.22019/) (2025)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://mlsanity.com/paper/2502.12342/) (2025)
- [Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education](https://mlsanity.com/paper/2502.05863/) (2025)
- [UniRAG: Universal Retrieval Augmentation for Large Vision Language Models](https://mlsanity.com/paper/2405.10311/) (2024)
- [Unanswerability Evaluation for Retrieval Augmented Generation](https://mlsanity.com/paper/2412.12300/) (2024)

## Built on by (most cited first, 21 of 21)

- [ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios](https://mlsanity.com/paper/2601.08620/) (2026)
- [Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding](https://mlsanity.com/paper/2510.15253/) (2025)
- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis](https://mlsanity.com/paper/2601.21403/) (2026)
- [MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents](https://mlsanity.com/paper/2603.05697/) (2026)
- [Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey](https://mlsanity.com/paper/2601.03262/) (2025)
- [MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects](https://mlsanity.com/paper/2608.29477/) (2026)
- [Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion](https://mlsanity.com/paper/2602.11960/) (2026)
- [Document-as-Image Representations Fall Short for Scientific Retrieval](https://mlsanity.com/paper/2604.18508/) (2026)
- [MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing](https://mlsanity.com/paper/2605.22100/) (2026)
- [Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG](https://mlsanity.com/paper/2607.05438/) (2026)
- [Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering](https://mlsanity.com/paper/2602.14162/) (2026)
- [MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs](https://mlsanity.com/paper/2602.23632/) (2026)
- [Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval](https://mlsanity.com/paper/2605.08421/) (2026)
- [KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval](https://mlsanity.com/paper/2608.01389/) (2026)
- [Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attribution](https://mlsanity.com/paper/2608.07943/) (2026)
- [D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding](https://mlsanity.com/paper/2608.16417/) (2026)
- [KoViDoRe: A Benchmark for Korean Visual Document Retrieval](https://mlsanity.com/paper/2608.20840/) (2026)
- [NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference](https://mlsanity.com/paper/2609.01657/) (2026)
- [Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents](https://mlsanity.com/paper/2610.08452/) (2026)
- [TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning](https://mlsanity.com/paper/2610.09360/) (2026)

## Abstract (arXiv)

Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are fragmented -- focusing on either text or images in isolation, or simplified multimodal setup, failing to capture document-centric multimodal use cases. In this paper, we introduce UniDoc-Bench, the first large-scale, realistic benchmark for MM-RAG built from k real-world PDF pages across domains. Our pipeline extracts and links evidence from text, tables, and figures, then generates multimodal QA pairs spanning factual retrieval, comparison, summarization, and logical reasoning queries. To ensure reliability, all of QA pairs are validated by multiple human annotators and expert adjudication. UniDoc-Bench supports apples-to-apples comparison across four paradigms: 1) text-only, 2) image-only, 3) multimodal text-image fusion and 4) multimodal joint retrieval -- under a unified protocol with standardized candidate pools, prompts, and evaluation metrics. UniDoc-Bench can also be used to evaluate Visual Question Answering (VQA) tasks. Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval, indicating that neither text nor images alone are sufficient and that current multimodal embeddings remain inadequate. Beyond benchmarking, our analysis reveals when and how visual context complements textual evidence, uncovers systematic failure modes, and offers actionable guidance for developing more robust MM-RAG pipelines.