Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.05446 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915278439317504 |
|---|---|
| author | Xiao, Han Xie, Yina Tan, Guanxin Chen, Yinghao Hu, Rui Wang, Ke Zhou, Aojun Li, Hao Shao, Hao Lu, Xudong Gao, Peng Wen, Yafei Chen, Xiaoxin Ren, Shuai Li, Hongsheng |
| author_facet | Xiao, Han Xie, Yina Tan, Guanxin Chen, Yinghao Hu, Rui Wang, Ke Zhou, Aojun Li, Hao Shao, Hao Lu, Xudong Gao, Peng Wen, Yafei Chen, Xiaoxin Ren, Shuai Li, Hongsheng |
| contents | Visual Document Understanding has become essential with the increase of text-rich visual content. This field poses significant challenges due to the need for effective integration of visual perception and textual comprehension, particularly across diverse document types with complex layouts. Moreover, existing fine-tuning datasets for this domain often fall short in providing the detailed contextual information for robust understanding, leading to hallucinations and limited comprehension of spatial relationships among visual elements. To address these challenges, we propose an innovative pipeline that utilizes adaptive generation of markup languages, such as Markdown, JSON, HTML, and TiKZ, to build highly structured document representations and deliver contextually-grounded responses. We introduce two fine-grained structured datasets: DocMark-Pile, comprising approximately 3.8M pretraining data pairs for document parsing, and DocMark-Instruct, featuring 624k fine-tuning data annotations for grounded instruction following. Extensive experiments demonstrate that our proposed model significantly outperforms existing state-of-theart MLLMs across a range of visual document understanding benchmarks, facilitating advanced reasoning and comprehension capabilities in complex visual scenarios. Our code and models are released at https://github. com/Euphoria16/DocMark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05446 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding Xiao, Han Xie, Yina Tan, Guanxin Chen, Yinghao Hu, Rui Wang, Ke Zhou, Aojun Li, Hao Shao, Hao Lu, Xudong Gao, Peng Wen, Yafei Chen, Xiaoxin Ren, Shuai Li, Hongsheng Computer Vision and Pattern Recognition Computation and Language Visual Document Understanding has become essential with the increase of text-rich visual content. This field poses significant challenges due to the need for effective integration of visual perception and textual comprehension, particularly across diverse document types with complex layouts. Moreover, existing fine-tuning datasets for this domain often fall short in providing the detailed contextual information for robust understanding, leading to hallucinations and limited comprehension of spatial relationships among visual elements. To address these challenges, we propose an innovative pipeline that utilizes adaptive generation of markup languages, such as Markdown, JSON, HTML, and TiKZ, to build highly structured document representations and deliver contextually-grounded responses. We introduce two fine-grained structured datasets: DocMark-Pile, comprising approximately 3.8M pretraining data pairs for document parsing, and DocMark-Instruct, featuring 624k fine-tuning data annotations for grounded instruction following. Extensive experiments demonstrate that our proposed model significantly outperforms existing state-of-theart MLLMs across a range of visual document understanding benchmarks, facilitating advanced reasoning and comprehension capabilities in complex visual scenarios. Our code and models are released at https://github. com/Euphoria16/DocMark. |
| title | Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2505.05446 |