MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dai, Sijun, Huang, Qiang, You, Xiaoxing, Yu, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908940918325248
author Dai, Sijun
Huang, Qiang
You, Xiaoxing
Yu, Jun
author_facet Dai, Sijun
Huang, Qiang
You, Xiaoxing
Yu, Jun
contents Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while current graph-based methods rely on costly ``translation-to-text'' pipelines that discard fine-grained visual information. To address these limitations, we propose \textbf{MG$^2$-RAG}, a lightweight \textbf{M}ulti-\textbf{G}ranularity \textbf{G}raph \textbf{RAG} framework that jointly improves graph construction, modality fusion, and cross-modal retrieval. MG$^2$-RAG constructs a hierarchical multimodal knowledge graph by combining lightweight textual parsing with entity-driven visual grounding, enabling textual entities and visual regions to be fused into unified multimodal nodes that preserve atomic evidence. Building on this representation, we introduce a multi-granularity graph retrieval mechanism that aggregates dense similarities and propagates relevance across the graph to support structured multi-hop reasoning. Extensive experiments across four representative multimodal tasks (i.e., retrieval, knowledge-based VQA, reasoning, and classification) demonstrate that MG$^2$-RAG consistently achieves state-of-the-art performance while reducing graph construction overhead with an average 43.3$\times$ speedup and 23.9$\times$ cost reduction compared with advanced graph-based frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04969
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
Dai, Sijun
Huang, Qiang
You, Xiaoxing
Yu, Jun
Information Retrieval
Artificial Intelligence
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while current graph-based methods rely on costly ``translation-to-text'' pipelines that discard fine-grained visual information. To address these limitations, we propose \textbf{MG$^2$-RAG}, a lightweight \textbf{M}ulti-\textbf{G}ranularity \textbf{G}raph \textbf{RAG} framework that jointly improves graph construction, modality fusion, and cross-modal retrieval. MG$^2$-RAG constructs a hierarchical multimodal knowledge graph by combining lightweight textual parsing with entity-driven visual grounding, enabling textual entities and visual regions to be fused into unified multimodal nodes that preserve atomic evidence. Building on this representation, we introduce a multi-granularity graph retrieval mechanism that aggregates dense similarities and propagates relevance across the graph to support structured multi-hop reasoning. Extensive experiments across four representative multimodal tasks (i.e., retrieval, knowledge-based VQA, reasoning, and classification) demonstrate that MG$^2$-RAG consistently achieves state-of-the-art performance while reducing graph construction overhead with an average 43.3$\times$ speedup and 23.9$\times$ cost reduction compared with advanced graph-based frameworks.
title MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.04969