Document Parsing

Follow this topic Ask about this topic

Document parsing turns PDFs and page images into structured content that can support search, retrieval-augmented generation, and automated workflows. Systems range from OCR and layout-detection pipelines to end-to-end vision-language models, with training methods such as synthetic data, reinforcement learning, and parallel decoding. Evaluation increasingly tests tables, formulas, reading order, multilingual content, and multi-page structure across digital, degraded, and camera-captured documents. A central challenge is achieving reliable structural and semantic fidelity on real-world documents while keeping inference fast and affordable.

Latest papers

63 papers6 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting
Feb 17, 2026Md Mofijul Islam, Md Sirajus Salekin, Nivedha Balakrishnan +6Document Image Understanding Document Parsing
Amazon Web Services
HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding
Feb 13, 2026Wenhui Liao, Hongliang Li, Pengyu Xie +15Efficient VLM Inference Speculative Decoding
South China University of Technology, Guangzhou, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · Nanjing University, Nanjing, China +1
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
Jan 28, 2026Haoyu Cao, Kun Yin, Yunfei Wu +16Efficient VLM Inference Document Parsing
Youtu-Parsing Team*

Feb 17, 2026J/K move · Enter open · S save

DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting

Md Mofijul Islam, Md Sirajus Salekin, Nivedha Balakrishnan, Vincil C. Bishop+5

Amazon Web Services

Document Image Understanding Document Parsing Multimodal Model Evaluation Document Chunking

Open paper AskPDF arXiv

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.

Latest papers

DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting

HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding