Multimodal large language models (MLLMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page visually-rich documents. Traditional methods using document parsers for retrieval-augmented generation suffer from performance and efficiency limitations, while directly presenting all pages to MLLMs leads to inefficiencies, especially with lengthy ones. In this work, we present a novel framework named **S**elf-**V**isual **R**etrieval-**A**ugmented **G**eneration (SV-RAG), which can broaden horizons of any MLLM to support long-document understanding. We demonstrate that **MLLMs themselves can be an effective multimodal retriever** to fetch relevant pages and then answer user questions based on these pages. SV-RAG is implemented with two specific MLLM adapters, one for evidence page retrieval and the other for question answering. Empirical results show state-of-the-art performance on public benchmarks, demonstrating the effectiveness of SV-RAG.
View on arXiv@article{chen2025_2411.01106,
title={ SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding },
author={ Jian Chen and Ruiyi Zhang and Yufan Zhou and Tong Yu and Franck Dernoncourt and Jiuxiang Gu and Ryan A. Rossi and Changyou Chen and Tong Sun },
journal={arXiv preprint arXiv:2411.01106},
year={ 2025 }
}