DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914336115523584 |
|---|---|
| author | Islam, Md Mofijul Salekin, Md Sirajus Balakrishnan, Nivedha Bishop III, Vincil C. Jain, Niharika Romo, Spencer Strahan, Bob Xie, Boyi Socolinsky, Diego A. |
| author_facet | Islam, Md Mofijul Salekin, Md Sirajus Balakrishnan, Nivedha Bishop III, Vincil C. Jain, Niharika Romo, Spencer Strahan, Bob Xie, Boyi Socolinsky, Diego A. |
| contents | Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the fundamental task of document packet splitting, which involves separating a document packet into individual units, remains largely unaddressed. We present the first comprehensive benchmark dataset, DocSplit, along with novel evaluation metrics for assessing the document packet splitting capabilities of large language models. DocSplit comprises five datasets of varying complexity, covering diverse document types, layouts, and multimodal settings. We formalize the DocSplit task, which requires models to identify document boundaries, classify document types, and maintain correct page ordering within a document packet. The benchmark addresses real-world challenges, including out-of-order pages, interleaved documents, and documents lacking clear demarcations. We conduct extensive experiments evaluating multimodal LLMs on our datasets, revealing significant performance gaps in current models' ability to handle complex document splitting tasks. The DocSplit benchmark datasets and proposed novel evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains. We release the datasets to facilitate future research in document packet processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15958 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting Islam, Md Mofijul Salekin, Md Sirajus Balakrishnan, Nivedha Bishop III, Vincil C. Jain, Niharika Romo, Spencer Strahan, Bob Xie, Boyi Socolinsky, Diego A. Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the fundamental task of document packet splitting, which involves separating a document packet into individual units, remains largely unaddressed. We present the first comprehensive benchmark dataset, DocSplit, along with novel evaluation metrics for assessing the document packet splitting capabilities of large language models. DocSplit comprises five datasets of varying complexity, covering diverse document types, layouts, and multimodal settings. We formalize the DocSplit task, which requires models to identify document boundaries, classify document types, and maintain correct page ordering within a document packet. The benchmark addresses real-world challenges, including out-of-order pages, interleaved documents, and documents lacking clear demarcations. We conduct extensive experiments evaluating multimodal LLMs on our datasets, revealing significant performance gaps in current models' ability to handle complex document splitting tasks. The DocSplit benchmark datasets and proposed novel evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains. We release the datasets to facilitate future research in document packet processing. |
| title | DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.15958 |