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.

PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing
Jun 3, 2026Maksim Shandybo, Ivan Bespalov, Daniil Yefimov +2Historical Document Analysis Multimodal Robustness
1IGIC RAS, Moscow, Russian Federation · 2Yandex Cloud, Moscow, Russian Federation · 3National University of Science and Technology MISIS, Moscow, Russian Federation +1
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Jun 2, 2026Zelun Zhang, Hongen Liu, Suyin Liang +12Data Selection Training Data Selection
PaddlePaddle Team, Baidu Inc.
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
May 31, 2026Minglai Yang, Xinyan Velocity Yu, Pengyuan Li +22VLM Evaluation Document Parsing Benchmarks
2077AI · University of Arizona · University of Southern California +8
ABot-OCR Technical Report
May 27, 2026Kaitao Jiang, Ruiyan Gong, Xiaolong Cheng +3Vision-Language Models Document Parsing
AMAP CV Lab Alibaba Group
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
May 24, 2026Bangrui Xu, Ziyang Miao, Xuanhe Zhou +8Document Parsing
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory, OpenDataLab · University of California, Berkeley
AI-Friendly LaTeX: Using LaTeX Code as a Knowledge Source for Retrieval-Augmented Generation
May 21, 2026Tom VerhoeffRetrieval-Augmented Generation Knowledge Augmentation for Language Models
Department of Mathematics & Computer Science, Eindhoven University of Technology
MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing
May 21, 2026Bangbang Zhou, Hangdi Xing, Yifan Chen +8Document Parsing Benchmarks Document Parsing
University of Science and Technology of China · Tongyi Lab, Alibaba Group
How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence
May 19, 2026Yue Chen, Yihao Wang, Ziyi Tang +2Document Parsing Document Layout Analysis
Sun Yat-sen University · Chaotic Pendulum Lab · Nanyang Technological University
How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings
May 8, 2026Zhiheng Li, Zongyang Ma, Jiaxian Chen +12Document Parsing Benchmarks Document Parsing
CASIA · UCAS · Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information +6
Lightweight and Production-Ready PDF Visual Element Parsing
Apr 25, 2026Meizhu Liu, Yassi Abbasi, Matthew Rowe +2Document Parsing Document Layout Analysis
Oracle AI
M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
Apr 17, 2026Joongmin Shin, Jeongbae Park, Jaehyung Seo +1Multimodal RAG Document Chunking
Human-inspired AI Research, Korea University · Computer Science and Engineering, Konkuk University · Department of Computer Science and Engineering, Korea University
MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
Apr 14, 2026Joongmin Shin, Chanjun Park, Jeongbae Park +2Document Chunking Multimodal RAG
Human-inspired AI Research, Korea University · School of Software, Soongsil University · Department of Computer Science and Engineering, Korea University
Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
Apr 13, 2026Omar El Bachyr, Yewei Song, Saad Ezzini +5Document Parsing RAG Evaluation
University of Luxembourg Luxembourg, Luxembourg · King Fahd University of Petroleum and Minerals Dhahran, Saudi Arabia · BGL BNP Paribas Luxembourg, Luxembourg
ParseBench: A Document Parsing Benchmark for AI Agents
Apr 9, 2026Boyang Zhang, Sebastián G. Acosta, Preston Carlson +4Document Parsing Benchmarks Document Parsing
Instruction-Tuned LLMs for Parsing and Mining Unstructured Logs on Leadership HPC Systems
Apr 6, 2026Ahmad Maroof Karimi, Jong Youl Choi, Charles Qing Cao +1Document Parsing LLM Information Extraction
Oak Ridge National Laboratory, Oak Ridge, USA · University of Tennessee, Knoxville, USA
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Apr 6, 2026Bin Wang, Tianyao He, Linke Ouyang +40Document Parsing Training Data Curation
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
Apr 3, 2026Fuyuan Liu, Dianyu Yu, He Ren +10Document Parsing Document Layout Analysis
Unisound AI Technology Co., Ltd. China · School of Computer Science and Technology, Tianjin University China · MAIS, Institute of Automation, Chinese Academy of Sciences China
AutoFormBench: Benchmark Dataset for Automating Form Understanding
Mar 31, 2026Gaurab Baral, Junxiu ZhouDocument Understanding Document Layout Analysis
School of Computing and Analytics, Northern Kentucky University, Highland Heights, Kentucky, 41076
From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
Mar 30, 2026José Guilherme Marques dos Santos, Ricardo Yang, Rui Humberto Pereira +8Document Parsing RAG Evaluation
Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal · Department of Business Administration, University of Maia, 4475-690 Maia, Portugal · LIACC—Artificial Intelligence and Computer Science Laboratory, University of Porto, 4200-465 Porto, Portugal +3
Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
Mar 25, 2026Cheng Cui, Ting Sun, Suyin Liang +15Document Parsing Document Image Understanding
PaddlePaddle Team, Baidu Inc. · Xi’an Jiaotong University
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
Mar 25, 2026Gengluo Li, Pengyuan Lyu, Chengquan Zhang +7Document Parsing Multimodal Large Language Models
Institute of Information Engineering, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Tencent +2
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
Mar 16, 2026Pengfei Yue, Xingran Zhao, Juntao Chen +6Multilingual VLM Evaluation Document Parsing
Xiamen University, China · Shopee, China · Tongji University, China
Efficient Document Parsing via Parallel Token Prediction
Mar 16, 2026Lei Li, Ze Zhao, Meng Li +6Efficient VLM Inference Document Parsing
Platform and Content Group, Tencent · Renmin University of China
Multimodal OCR: Parse Anything from Documents
Mar 13, 2026Handong Zheng, Yumeng Li, Kaile Zhang +22Document Parsing Document Image Understanding
Huazhong University of Science and Technology · hi lab, Xiaohongshu Inc
LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference
Mar 11, 2026Siyi Qian, Xiongfei Bai, Bingtao Fu +4Table Structure Recognition Document Parsing
Ant Group
Tabular PDF Information Extraction with Local LLMs and Layout-Aware Parsing: A Reliability Evaluation
Mar 9, 2026Muhammad Anis Al Hilmi, Neelansh Khare, Noel Framil Iglesias +3Document Information Extraction Document Parsing
Informatics, Faculty of Engineering, Universitas Swadaya Gunung Jati, Cirebon, Indonesia · Computer Science, University of California, Irvine, USA · Computer Engineering, UNIR, La Rioja, Spain +1
Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild
Mar 4, 2026Changda Zhou, Ziyue Gao, Xueqing Wang +4VLM Evaluation Document Parsing Benchmarks
PaddlePaddle Team, Baidu Inc. · The Hong Kong University of Science and Technology (Guangzhou)
FireRed-OCR Technical Report
Mar 2, 2026Hao Wu, Haoran Lou, Xinyue Li +19Optical Character Recognition Document Parsing
Super Intelligence Team, Xiaohongshu Inc.
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining
Feb 23, 2026Jeffrey Li, Josh Gardner, Doug Kang +10Training Data Extraction Document Parsing
University of Washington · Apple · Stanford
NovaLAD: A Fast, CPU-Optimized Document Extraction Pipeline for Generative AI and Data Intelligence
Feb 23, 2026Aman UllaDocument Information Extraction Document Parsing

Jun 3, 2026J/K move · Enter open · S save

PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing

Maksim Shandybo, Ivan Bespalov, Daniil Yefimov, Marina Kosheleva+1

1IGIC RAS, Moscow, Russian Federation · 2Yandex Cloud, Moscow, Russian Federation · 3National University of Science and Technology MISIS, Moscow, Russian Federation+1

Historical Document Analysis Multimodal Robustness Document Parsing Document Layout Analysis Historical Document Processing

Open paper AskPDF arXiv

Parsing historical documents with complex, non-standard layouts remains a fundamental bottleneck in large-scale archival digitization. Unlike modern typography, historical newspapers exhibit severe physical degradation and highly irregular page structures that confound even state-of-the-art vision-language models, presenting severe out-of-distribution challenges. We address this gap with an automated pipeline specifically designed for parsing historical newspapers, documents characterized by particularly intricate multi-column layouts. Our approach combines a fine-tuned YOLO architecture for layout analysis and block detection, trained on 1,426 fully human-annotated scanned pages, with a novel semantic assembly module that reconstructs articles by jointly modeling lexical-semantic similarity via TF-IDF, visual embeddings from our fine-tuned YOLO, and geometric layout constraints. This multi-modal integration yields state-of-the-art performance, achieving an F1 score of 0.904 on block-to-article mapping. Notably, end-to-end evaluation against vision-language models (Qwen3.6-35B-A3B and Qwen3.6-Plus) demonstrates that PereStruct achieves substantially higher fidelity (BLEU approximately 0.96 vs 0.34), validating that modular architectures excel where generic VLMs fail on complex historical layouts. To support reproducibility and advance research in this domain, we release both the training corpus of 599 annotated pages and a curated PereStruct benchmark of 93 pages with expert-verified ground-truth block-to-article mappings. This framework establishes a robust foundation for high-fidelity digitization and semantic reconstruction of complex archival materials.