Document Information Extraction

Ask about this topic

Overview

Document information extraction studies how to convert documents into structured fields, entities, relations, events, and tables that can support search, analysis, and decision-making. Common approaches combine OCR and layout analysis with supervised sequence taggers, schema-guided language models, multimodal models, retrieval, and deterministic validation. Work spans receipts and forms as well as long clinical, financial, legal, and scientific documents, with benchmarks increasingly testing noisy inputs, layout understanding, source grounding, and output completeness. A central challenge is balancing flexible semantic interpretation with exact values, boundaries, and reliable evidence, while keeping systems efficient and robust across document types.

Latest papers

CardsList

290 papers31 papers in the last four weeks, down 39% on the four weeks before. 0.2% of all new papers.

  1. ParseBench: A Document Parsing Benchmark for AI Agents

    Apr 9, 2026Boyang Zhang, Sebastián G. Acosta, Preston Carlson +4Document Parsing BenchmarksDocument Parsing

  2. From Papers to Property Tables: A Priority-Based LLM Workflow for Materials Data Extraction

    Apr 8, 2026Koushik Rameshbabu, Jing Luo, Ali Shargh +2Document Information ExtractionLLM Information Extraction

    Department of Applied Mathematics and Statistics, Johns Hopkins University · Department of Mechanical Engineering, Johns Hopkins University

  3. FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts

    Apr 8, 2026Guillermo Gil de Avalle, Laura Maruster, Eric Sloot +1Document Information ExtractionChart Understanding

    University of Groningen, Nettelbosje 2, Groningen, The Netherlands · Philips Consumer Lifestyle B.V., Oliemolenstraat 5, Drachten, The Netherlands

  4. LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources

    Apr 8, 2026Joshua Castillo, Ravi MukkamalaDocument Information ExtractionLLM Information Extraction

    Department of Computer Science Old Dominion University Norfolk, Virginia, USA

  5. STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System

    Apr 7, 2026Wenxiao Zhang, Yu Liu, Qiang sun +5Document Information ExtractionLLM Information Extraction

    The University of Western Australia Perth, Australia · Institute of Information Engineering, Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing, China · Murdoch University Perth, Australia

  6. Chronos: The AI Co-Historian

    Apr 4, 2026Lorenz Hufe, Niclas Griesshaber, Gavin Greif +5Historical Document AnalysisAI-Assisted Scientific Research

    Fraunhofer HHI · University of Oxford · The Alan Turing Institute +2

  7. De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

    Apr 2, 2026Keerat Guliani, Deepkamal Gill, David Landsman +3Document Information ExtractionLegal Document Analysis

    The Vanguard Group, Inc.

  8. A Role-Based LLM Framework for Structured Information Extraction from Healthy Food Policies

    Apr 2, 2026Congjing Zhang, Ruoxuan Bao, Jingyu Li +3Document Information ExtractionLLM Information Extraction

    Department of Industrial & Systems Engineering, University of Washington, Seattle, WA, USA · Department of Management, Shanghai University, Shanghai, China · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA +1

  9. Information Extraction from Electricity Invoices with General-Purpose Large Language Models

    Apr 1, 2026Javier Gómez, Javier SánchezDocument Information ExtractionLLM Information Extraction

    Centro de Tecnologías de la Imagen (CTIM) Instituto Universitario de Cibernética, Empresas y Sociedad (IUCES) Universidad de Las Palmas de Gran Canaria 35017 Las Palmas de Gran Canaria, Spain · Centro de Tecnologías de la Imagen (CTIM) Instituto Universitario de Cibernética, Empresas y Sociedad (IUCES) University of Las Palmas de Gran Canaria 35017 Las Palmas de Gran Canaria, Spain

  10. Quid est VERITAS? A Modular Framework for Archival Document Analysis

    Mar 30, 2026Leonardo Bassanini, Ludovico Biancardi, Alfio Ferrara +3Historical Document AnalysisHistorical Document Processing

    Università degli Studi di Milano, University Library Service Via Santa Sofia, 7/9 - 20122 Milano (Italy) · Università degli Studi di Milano, Department of Literary Studies, Philology and Linguistics Via Festa del Perdono, 7 - 20122 Milano (Italy) · Università degli Studi di Milano, Department of Historical Studies Via Festa del Perdono, 7 - 20122 Milano (Italy) +1

  11. Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models

    Mar 30, 2026Luigi Curini, Alfio Ferrara, Giovanni Pagano +1Document Information ExtractionDocument Understanding

    Università degli Studi di Milano, Department of Social and Political Sciences, Via Conservatorio, 7 - 20122 Milano (Italy) · Università degli Studi di Milano, Department of Literary Studies, Philology and Linguistics, Via Festa del Perdono, 7 - 20122 Milano (Italy) · Università degli Studi di Milano, Department of Computer Science, Via Celoria, 18 - 20133 Milano (Italy)

  12. ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction

    Mar 29, 2026Tsung-Yu Yang, Meng-Chi ChenDocument Information ExtractionEvidence-Grounded Generation

    Massachusetts Institute of Technology

  13. Methods for Knowledge Graph Construction from Text Collections: Development and Applications

    Mar 26, 2026Vanni ZavarellaKG ConstructionDocument Information Extraction

  14. RenoBench: A Citation Parsing Benchmark

    Mar 26, 2026Parth Sarin, Juan Pablo Alperin, Adam Buttrick +1Document Parsing BenchmarksDocument Information Extraction

    Graduate School of Education, Stanford University, Stanford, California, USA · Public Knowledge Project, Simon Fraser University, Vancouver, British Columbia, Canada · California Digital Library, University of California Office of the President, Oakland, California, USA +1

  15. Benchmarking Multi-Agent LLM Architectures for Financial Document Processing: A Comparative Study of Orchestration Patterns, Cost-Accuracy Tradeoffs and Production Scaling Strategies

    Mar 24, 2026Siddhant Kulkarni, Yukta KulkarniMulti-Agent LLM SystemsLLM Agent Orchestration

    Department of Computer Science and Engineering, New York University, New York, NY 10012

  16. TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols

    Mar 22, 2026Saketh Vinjamuri, Marielle Fis Loperena, Marie C. Spezia +1Clinical Information ExtractionDocument Information Extraction

    Fairview Hospital, Cleveland Clinic Foundation, Cleveland, OH, USA · The George Washington University School of Medicine and Health Sciences, Washington, DC, USA · University of Missouri-Columbia School of Medicine, Columbia, MO, USA +1

  17. Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles

    Mar 22, 2026Sai Koneru, Jian Wu, Sarah RajtmajerDocument Information ExtractionLLM Information Extraction

    Pennsylvania State University, University Park, Pennsylvania, USA · Old Dominion University, Norfolk, Virginia, USA

  18. Beyond String Matching: Semantic Evaluation of PDF Table Extraction

    Mar 19, 2026Pius Horn, Janis KeuperDocument Parsing BenchmarksDocument Information Extraction

    Institute for Machine Learning and Analytics (IMLA), Offenburg University, Offenburg, Germany · University of Mannheim, Mannheim, Germany

  19. SODIUM: From Open Web Data to Queryable Databases

    Mar 19, 2026Chuxuan Hu, Philip Li, Maxwell Yang +1Web Search AgentsWeb Agents

    UIUC

  20. SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction

    Mar 16, 2026David Števaňák, Marek ŠuppaDocument Information ExtractionLow-Resource Language Processing

    University of Vienna, Austria · NaiveNeuron · Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava +1

  21. VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents

    Mar 16, 2026Udi Barzelay, Ophir Azulai, Inbar Shapira +4Document Information ExtractionMultimodal Model Evaluation

    IBM Research

  22. AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation

    Mar 16, 2026Haoxuan Zhang, Ruochi Li, Zhenni Liang +7Document Information ExtractionGenerative AI Evaluation

  23. LiveWeb-IE: A Benchmark For Online Web Information Extraction

    Mar 14, 2026Seungbin Yang, Jihwan Kim, Jaemin Choi +4Document Information ExtractionWeb Agents

    KAIST AI · Letsur · School of Computer Science and Engineering, Chung-Ang University

  24. Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities

    Mar 13, 2026Yurui Zhu, Giovanni Colavizza, Matteo RomanelloDocument Information ExtractionLLM Information Extraction

    Odoma LLC

  25. Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling

    Mar 12, 2026Sayantan Kumar, Jeremy C. WeissClinical Information ExtractionDocument Information Extraction

    National Library of Medicine, Bethesda, Maryland, USA

  26. Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

    Mar 11, 2026Daxiang Dong, Mingming Zheng, Dong Xu +17Document Image UnderstandingOptical Character Recognition

  27. 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 ExtractionDocument 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

  28. A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text

    Mar 8, 2026Fei Cheng, Ribeka Tanaka, Sadao KurohashiClinical Information ExtractionRelation Extraction

    Kyoto University · Tokyo University of Technology · National Institute of Informatics

  29. A Dynamic Self-Evolving Extraction System

    Mar 6, 2026Moin Amin-Naseri, Hannah Kim, Estevam HruschkaDocument Information ExtractionLLM Information Extraction

    Megagon Labs

  30. OpenExtract: Automated Data Extraction for Systematic Reviews in Health

    Mar 6, 2026Jim Achterberg, Bram Van Dijk, Jing Meng +8Systematic Review AutomationDocument Information Extraction

    Leiden University Medical Center, The Netherlands · Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands · University of Warwick, UK +2