# MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation

arXiv: https://arxiv.org/abs/2602.10271 · HTML: https://mlsanity.com/paper/2602.10271/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [A Comprehensive Survey of Deep Learning for Image Captioning](https://mlsanity.com/paper/1810.04020/) (2018)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD](https://mlsanity.com/paper/2404.06512/) (2024)
- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms](https://mlsanity.com/paper/1807.05614/) (2018)
- [LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating](https://mlsanity.com/paper/2412.18424/) (2024)
- [DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections](https://mlsanity.com/paper/2508.15851/) (2025)

## Built on by (most cited first, 4 of 4)

- [MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA](https://mlsanity.com/paper/2606.15906/) (2026)
- [Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing](https://mlsanity.com/paper/2606.01393/) (2026)
- [HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation](https://mlsanity.com/paper/2608.14032/) (2026)
- [MM-ContextFold: Context Folding for Multimodal Agentic Retrieval](https://mlsanity.com/paper/2609.23121/) (2026)

## Abstract (arXiv)

Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal heterogeneity to localize relevant information across modalities, (2) cross-page reasoning to aggregate dispersed evidence across pages. To address these challenges, we are motivated to adopt a query-centric formulation that projects cross-modal and cross-page information into a unified query representation space, with queries acting as abstract semantic surrogates for heterogeneous multimodal content. In this paper, we propose a Multimodal Long-Context Document Retrieval Augmented Generation (MLDocRAG) framework that leverages a Multimodal Chunk-Query Graph (MCQG) to organize multimodal document content around semantically rich, answerable queries. MCQG is constructed via a multimodal document expansion process that generates fine-grained queries from heterogeneous document chunks and links them to their corresponding content across modalities and pages. This graph-based structure enables selective, query-centric retrieval and structured evidence aggregation, thereby enhancing grounding and coherence in multimodal long-context question answering. Experiments on datasets MMLongBench-Doc and LongDocURL demonstrate that MLDocRAG consistently improves retrieval quality and answer accuracy, demonstrating its effectiveness for multimodal long-context understanding.