paper-with-me

Papers

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

2023-07-04 · Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Yuhao Dan, Chenlin Zhao, Guohai Xu, Chenliang Li, Junfeng Tian, Qian Qi, Ji Zhang, Fei Huang

Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-Owl, have demonstrated promising zero-shot capabilities in shallow OCR-free text recognition, indicating their potential for OCR-free document understanding. Nevertheless, without in-domain training, these models tend to ignore fine-grained OCR features, such as sophisticated tables or large blocks of text, which are essential for OCR-free document understanding. In this paper, we propose mPLUG-DocOwl based on mPLUG-Owl for OCR-free document understanding. Specifically, we first construct a instruction tuning dataset featuring a wide range of visual-text understanding tasks. Then, we strengthen the OCR-free document understanding ability by jointly train the model on language-only, general vision-and-language, and document instruction tuning dataset with our unified instruction tuning strategy. We also build an OCR-free document instruction understanding evaluation set LLMDoc to better compare models' capabilities on instruct compliance and document understanding. Experimental results show that our model outperforms existing multi-modal models, demonstrating its strong ability of document understanding. Besides, without specific fine-tuning, mPLUG-DocOwl generalizes well on various downstream tasks. Our code, models, training data and evaluation set are available at https://github.com/X-PLUG/mPLUG-DocOwl.

📄 PDF Abstract BibTeX arXiv:2307.02499

Code (1)

x-plug/mplug-docowl 공식 구현 pytorch

Tasks

document understandingLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelOptical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding

2024-09-05 · Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye 외

Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this comes at the cost of generating thousan…

document understandingGPUOptical Character Recognition (OCR)Question Answering

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding

2024-03-19 · Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan 외

Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipp…

document understandingOptical Character Recognition (OCR)

Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks

2023-06-07 · Haiyang Xu, Qinghao Ye, Xuan Wu, Ming Yan 외

To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named…

Cross-Modal RetrievalLanguage ModellingLarge Language ModelMultimodal Large Language Model+2

mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model

2023-11-30 · Anwen Hu, Yaya Shi, Haiyang Xu, Jiabo Ye 외

Recently, the strong text creation ability of Large Language Models(LLMs) has given rise to many tools for assisting paper reading or even writing. However, the weak diagram analysis abilities of LLMs or Multimodal LLMs …

Language ModelingLanguage ModellingLarge Language ModelMultimodal Large Language Model

mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

2023-04-27 · Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye 외

Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introd…

Visual Question Answering (VQA)Zero-Shot Video Question Answer