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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Sensen, Zhao, Shanshan, Jiang, Xu, Duan, Lunhao, Chng, Yong Xien, Chen, Qing-Guo, Luo, Weihua, Zhang, Kaifu, Bian, Jia-Wang, Gong, Mingming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915945207824384
author Gao, Sensen
Zhao, Shanshan
Jiang, Xu
Duan, Lunhao
Chng, Yong Xien
Chen, Qing-Guo
Luo, Weihua
Zhang, Kaifu
Bian, Jia-Wang
Gong, Mingming
author_facet Gao, Sensen
Zhao, Shanshan
Jiang, Xu
Duan, Lunhao
Chng, Yong Xien
Chen, Qing-Guo
Luo, Weihua
Zhang, Kaifu
Bian, Jia-Wang
Gong, Mingming
contents 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, applications and industry deployment, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15253
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
Gao, Sensen
Zhao, Shanshan
Jiang, Xu
Duan, Lunhao
Chng, Yong Xien
Chen, Qing-Guo
Luo, Weihua
Zhang, Kaifu
Bian, Jia-Wang
Gong, Mingming
Computation and Language
Computer Vision and Pattern Recognition
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, applications and industry deployment, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.
title Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.15253