Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tripathi, Vishesh, Odapally, Tanmay, Das, Indraneel, Allu, Uday, Ahmed, Biddwan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911053595541504
author Tripathi, Vishesh
Odapally, Tanmay
Das, Indraneel
Allu, Uday
Ahmed, Biddwan
author_facet Tripathi, Vishesh
Odapally, Tanmay
Das, Indraneel
Allu, Uday
Ahmed, Biddwan
contents Retrieval-Augmented Generation (RAG) systems have revolutionized information retrieval and question answering, but traditional text-based chunking methods struggle with complex document structures, multi-page tables, embedded figures, and contextual dependencies across page boundaries. We present a novel multimodal document chunking approach that leverages Large Multimodal Models (LMMs) to process PDF documents in batches while maintaining semantic coherence and structural integrity. Our method processes documents in configurable page batches with cross-batch context preservation, enabling accurate handling of tables spanning multiple pages, embedded visual elements, and procedural content. We evaluate our approach on a curated dataset of PDF documents with manually crafted queries, demonstrating improvements in chunk quality and downstream RAG performance. Our vision-guided approach achieves better accuracy compared to traditional vanilla RAG systems, with qualitative analysis showing superior preservation of document structure and semantic coherence.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16035
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Tripathi, Vishesh
Odapally, Tanmay
Das, Indraneel
Allu, Uday
Ahmed, Biddwan
Machine Learning
Artificial Intelligence
Information Retrieval
Retrieval-Augmented Generation (RAG) systems have revolutionized information retrieval and question answering, but traditional text-based chunking methods struggle with complex document structures, multi-page tables, embedded figures, and contextual dependencies across page boundaries. We present a novel multimodal document chunking approach that leverages Large Multimodal Models (LMMs) to process PDF documents in batches while maintaining semantic coherence and structural integrity. Our method processes documents in configurable page batches with cross-batch context preservation, enabling accurate handling of tables spanning multiple pages, embedded visual elements, and procedural content. We evaluate our approach on a curated dataset of PDF documents with manually crafted queries, demonstrating improvements in chunk quality and downstream RAG performance. Our vision-guided approach achieves better accuracy compared to traditional vanilla RAG systems, with qualitative analysis showing superior preservation of document structure and semantic coherence.
title Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2506.16035