PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908422176243712 |
|---|---|
| author | Ni, Feng Huang, Kui Lu, Yao Lv, Wenyu Wang, Guanzhong Chen, Zeyu Liu, Yi |
| author_facet | Ni, Feng Huang, Kui Lu, Yao Lv, Wenyu Wang, Guanzhong Chen, Zeyu Liu, Yi |
| contents | With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for fast and accurate parsing of the content in document images. Therefore, this report presents PP-DocBee, a novel multimodal large language model designed for end-to-end document image understanding. First, we develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization. Then, we apply a few training techniques, including dynamic proportional sampling, data preprocessing, and OCR postprocessing strategies. Extensive evaluations demonstrate the superior performance of PP-DocBee, achieving state-of-the-art results on English document understanding benchmarks and even outperforming existing open source and commercial models in Chinese document understanding. The source code and pre-trained models are publicly available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks Ni, Feng Huang, Kui Lu, Yao Lv, Wenyu Wang, Guanzhong Chen, Zeyu Liu, Yi Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for fast and accurate parsing of the content in document images. Therefore, this report presents PP-DocBee, a novel multimodal large language model designed for end-to-end document image understanding. First, we develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization. Then, we apply a few training techniques, including dynamic proportional sampling, data preprocessing, and OCR postprocessing strategies. Extensive evaluations demonstrate the superior performance of PP-DocBee, achieving state-of-the-art results on English document understanding benchmarks and even outperforming existing open source and commercial models in Chinese document understanding. The source code and pre-trained models are publicly available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}. |
| title | PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.04065 |