Document Information Extraction

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

305 papers21 papers in the last four weeks, down 38% on the four weeks before. 0.2% of all new papers.

  1. A Visual Information Extraction System Using Multimodal Large Language Models for Scanned Cognitive and Behavioral Assessments

    Nov 17, 2026Enshuo Hsu, Linh Nguyen, Sunyang Fu +5Document Information ExtractionClinical Information Extraction

  2. ANCHOR: Cluster-Grounded 5W1H Extraction via Large-Small Model Collaboration

    Nov 16, 2026Hongyu Jiang, Chenang Cai, Lei Gao +3Event ExtractionDocument Information Extraction

  3. Automated Knowledge Acquisition Pipeline for Disassembly Instructions: A Comparison of NLP and Generative AI Frameworks

    Nov 9, 2026Tim Schnieders, Tareq Maximilian Gabriel Ahrari, Oliver Petrovic +1Document Information ExtractionLLM Information Extraction

  4. Automatic keyphrase extraction and annotation: modern theoretical approaches and practical solutions for text and speech

    Nov 5, 2026Daria Guseva, Olga MitrofanovaDocument Information ExtractionSpeech Processing

  5. Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026

    Nov 2, 2026Warre Veys, Luis Gasco, Jens-Joris DecorteIR EvaluationDocument Information Extraction

  6. Unlocking Criminal Court Decisions: Flexible Information Extraction for Empirical Legal Research

    Nov 2, 2026Tomáš Knap, Ivana Kvapilíková, Jan Černý +4Document Information ExtractionLegal NLP

  7. RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures

    Nov 2, 2026Jinbo Hu, Songren Zhang, Chuanxun Fu +19Document Information ExtractionMultimodal Agents

  8. ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics

    Oct 31, 2026Dikshya Mohanty, Manoj Praveen Nandigama, Kuldeepsinh Raj +10Document Information ExtractionLLM Information Extraction

  9. Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages

    Oct 29, 2026Chutong Meng, Alec J. Bateman, Antonios AnastasopoulosLow-Resource Language ProcessingLow-Resource MT

  10. Towards Full-Text Scholarly Argument Mining using Entity-Anchored Claim Extraction

    Oct 29, 2026Bhuvanesh Verma, Andy Lüking, Mounika Marreddy +2Argument MiningDocument Information Extraction

  11. Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews

    Oct 26, 2026Pujan Pant, Sagar Newpane, Hari Sitaula +1LLM Information ExtractionDocument Information Extraction

  12. Xing USP: A Cross-Family Semantic Contract for Information Extraction and Intent-Slot Parsing

    Oct 25, 2026Zhongqiu Li, Boyang Wang, Ruiyu Fang +17Semantic ParsingDocument Information Extraction

  13. RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature

    Oct 23, 2026Jiaxing Sun, Junyuan Gao, Ruikang Zhang +16Multimodal DatasetDocument Information Extraction

  14. Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models

    Oct 21, 2026Aravindan Kamatchi Sundaram, B. Pabitramohan Prusty, Rohit BatraDocument Information ExtractionLLM Information Extraction

  15. OvisOCR3 Technical Report

    Oct 20, 2026Yu Xia, Yinglun Li, Yuhui Chen +12Optical Character RecognitionDocument Image Understanding

  16. GAIDA: Generative AI for Human-in-the-Loop Document Annotation

    Oct 19, 2026Islam Mesabah, Ali Elhosary, Priyabanta Sandulu +2Automated Data AnnotationHuman-in-the-Loop Annotation

  17. Decomposed Relation Extraction from Aviation Accident Narratives: Evaluating Transformer-Based Safety Knowledge Discovery under Relational Sparsity

    Oct 19, 2026Aziida Nanyonga, Mustafa Tahsin Yilmaz, Saad Ezzini +2Relation ExtractionDocument Information Extraction

  18. ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases

    Oct 15, 2026Jaeyoung Lee, Geonyeong Son, Misuk KimDocument Information Extraction

  19. Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction

    Oct 14, 2026Lingfei Qian, Yan Wang, Xueqing Peng +6Financial Language Model EvaluationDocument Information Extraction

  20. FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing

    Oct 13, 2026Ashman Mehra, Bryan Routledge, Jane JaeYeon Pyo +1Relation ExtractionLLM Evaluation

  21. The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization

    Oct 13, 2026Jiacheng Lin, Geoffrey Low, Nishit Agarwal +4Coding AgentsDocument Information Extraction

  22. From Conceptual EneMonIE to an Executable Backend: A Modular Architecture for Energy Information Extractionand Grounded Question Answering

    Oct 12, 2026Janik Lesage, Khadim Lô, and Jean-Sébastien DessureaultEvidence-Grounded QADocument Information Extraction