Saved in:
Bibliographic Details
Main Authors: Khan, Ainulla, Moyuru, Yamada, Akella, Srinidhi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.18450
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909811742867456
author Khan, Ainulla
Moyuru, Yamada
Akella, Srinidhi
author_facet Khan, Ainulla
Moyuru, Yamada
Akella, Srinidhi
contents Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based queries, RAG on multi-modal documents containing both texts and images has not been fully explored. Especially when fine-tuning does not work. This paper proposes BRIT, a novel multi-modal RAG framework that effectively unifies various text-image connections in the document into a multi-modal graph and retrieves the texts and images as a query-specific sub-graph. By traversing both image-to-text and text-to-image paths in the graph, BRIT retrieve not only directly query-relevant images and texts but also further relevant contents to answering complex cross-modal multi-hop questions. To evaluate the effectiveness of BRIT, we introduce MM-RAG test set specifically designed for multi-modal question answering tasks that require to understand the text-image relations. Our comprehensive experiments demonstrate the superiority of BRIT, highlighting its ability to handle cross-modal questions on the multi-modal documents.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18450
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BRIT: Bidirectional Retrieval over Unified Image-Text Graph
Khan, Ainulla
Moyuru, Yamada
Akella, Srinidhi
Computation and Language
Retrieval-Augmented Generation (RAG) has emerged as a promising technique to enhance the quality and relevance of responses generated by large language models. While recent advancements have mainly focused on improving RAG for text-based queries, RAG on multi-modal documents containing both texts and images has not been fully explored. Especially when fine-tuning does not work. This paper proposes BRIT, a novel multi-modal RAG framework that effectively unifies various text-image connections in the document into a multi-modal graph and retrieves the texts and images as a query-specific sub-graph. By traversing both image-to-text and text-to-image paths in the graph, BRIT retrieve not only directly query-relevant images and texts but also further relevant contents to answering complex cross-modal multi-hop questions. To evaluate the effectiveness of BRIT, we introduce MM-RAG test set specifically designed for multi-modal question answering tasks that require to understand the text-image relations. Our comprehensive experiments demonstrate the superiority of BRIT, highlighting its ability to handle cross-modal questions on the multi-modal documents.
title BRIT: Bidirectional Retrieval over Unified Image-Text Graph
topic Computation and Language
url https://arxiv.org/abs/2505.18450