Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding

• URL: http://arxiv.org/abs/2510.15253v1
• Date: Fri, 17 Oct 2025 02:33:16 GMT
• Title: Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
• Authors: Sensen Gao, Shanshan Zhao, Xu Jiang, Lunhao Duan, Yong Xien Chng, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, Jia-Wang Bian, Mingming Gong,
• Abstract summary: Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
• Score: 61.36285696607487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key limitations: the former loses structural detail, while the latter struggles with context modeling. Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, i.e., combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG. This approach enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence. Recognizing its importance, this paper presents a systematic survey of Multimodal RAG for document understanding. We propose a taxonomy based on domain, retrieval modality, and granularity, and review advances involving graph structures and agentic frameworks. We also summarize key datasets, benchmarks, and applications, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.

Related papers

• Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval [67.73095846666583]
  Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich data and precise information acquisition.<n>This paper presents the first comprehensive survey of the VDR landscape, specifically through the lens of the Multimodal Large Language Model (MLLM) era.
  arXiv  Detail & Related papers  (2026-02-23T15:27:41Z)
• MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation [3.537921035534424]
  Multimodal Chunk-Query Graph (MCQG) generates semantically rich, answerable queries from heterogeneous document chunks.<n>This graph-based structure enables selective, query-centric retrieval and structured evidence aggregation.<n>Experiments on datasets MMLongBench-Doc and LongDocURL demonstrate that MLDocRAG consistently improves retrieval quality and answer accuracy.
  arXiv  Detail & Related papers  (2026-02-10T20:29:10Z)
• Multimodal RAG for Unstructured Data:Leveraging Modality-Aware Knowledge Graphs with Hybrid Retrieval [1.160208922584163]
  We present a Modality-Aware Hybrid retrieval Architecture (MAHA) for multimodal question answering with reasoning through a modality-aware knowledge graph.<n>MAHA integrates dense vector retrieval with structured graph traversal, where the knowledge graph encodes cross-modal semantics and relationships.<n>Our work establishes a scalable and interpretable retrieval framework that advances RAG systems by enabling modality-aware reasoning over unstructured multimodal data.
  arXiv  Detail & Related papers  (2025-10-16T11:55:24Z)
• Zero-shot Multimodal Document Retrieval via Cross-modal Question Generation [47.714317480436215]
  PREMIR is a simple framework that leverages the broad knowledge of an MLLM to generate cross modal pre questions (preQs) before retrieval.<n> Experiments show that PREMIR achieves state of the art performance on out of distribution benchmarks, including closed domain and multilingual settings.
  arXiv  Detail & Related papers  (2025-08-23T16:14:41Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• A Multi-Granularity Retrieval Framework for Visually-Rich Documents [4.804551482123172]
  We propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR.<n>Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering.<n>Our framework demonstrates robust performance without the need for task-specific fine-tuning.
  arXiv  Detail & Related papers  (2025-05-01T02:40:30Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.7225771305861]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M$2$RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models.<n>The benchmark comprises four tasks: image captioning, multi-modal question answering, multi-modal fact verification, and image reranking.<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation [100.06122876025063]
  This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings.<n>We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG.
  arXiv  Detail & Related papers  (2024-12-14T06:24:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.