Towards Visual Text Grounding of Multimodal Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Ming, Zhang, Ruiyi, Chen, Jian, Wang, Chenguang, Gu, Jiuxiang, Zhou, Yufan, Dernoncourt, Franck, Zhu, Wanrong, Zhou, Tianyi, Sun, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918146803236864
author Li, Ming
Zhang, Ruiyi
Chen, Jian
Wang, Chenguang
Gu, Jiuxiang
Zhou, Yufan
Dernoncourt, Franck
Zhu, Wanrong
Zhou, Tianyi
Sun, Tong
author_facet Li, Ming
Zhang, Ruiyi
Chen, Jian
Wang, Chenguang
Gu, Jiuxiang
Zhou, Yufan
Dernoncourt, Franck
Zhu, Wanrong
Zhou, Tianyi
Sun, Tong
contents Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documents. Document images, such as scanned forms and infographics, highlight critical challenges due to their complex layouts and textual content. However, current benchmarks do not fully address these challenges, as they mostly focus on visual grounding on natural images, rather than text-rich document images. Thus, to bridge this gap, we introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking and improving the Text-Rich Image Grounding capabilities of MLLMs in document question-answering. Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark and a large-scale training set of 90$ synthetic data based on four diverse datasets. A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images. In addition, we propose two simple and effective TRIG methods based on general instruction tuning and plug-and-play efficient embedding, respectively. By finetuning MLLMs on our synthetic dataset, they promisingly improve spatial reasoning and grounding capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Visual Text Grounding of Multimodal Large Language Model
Li, Ming
Zhang, Ruiyi
Chen, Jian
Wang, Chenguang
Gu, Jiuxiang
Zhou, Yufan
Dernoncourt, Franck
Zhu, Wanrong
Zhou, Tianyi
Sun, Tong
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-rich images of documents. Document images, such as scanned forms and infographics, highlight critical challenges due to their complex layouts and textual content. However, current benchmarks do not fully address these challenges, as they mostly focus on visual grounding on natural images, rather than text-rich document images. Thus, to bridge this gap, we introduce TRIG, a novel task with a newly designed instruction dataset for benchmarking and improving the Text-Rich Image Grounding capabilities of MLLMs in document question-answering. Specifically, we propose an OCR-LLM-human interaction pipeline to create 800 manually annotated question-answer pairs as a benchmark and a large-scale training set of 90$ synthetic data based on four diverse datasets. A comprehensive evaluation of various MLLMs on our proposed benchmark exposes substantial limitations in their grounding capability on text-rich images. In addition, we propose two simple and effective TRIG methods based on general instruction tuning and plug-and-play efficient embedding, respectively. By finetuning MLLMs on our synthetic dataset, they promisingly improve spatial reasoning and grounding capabilities.
title Towards Visual Text Grounding of Multimodal Large Language Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2504.04974