LLM Information Extraction

LLM: Large Language Model

Overview

This field studies how to turn text, tables, images, and long documents into structured data that can support search, analysis, and decision-making. Common tasks include named-entity and relation extraction, event and attribute extraction, clinical report parsing, and building knowledge graphs from scientific or legal literature. Approaches range from prompting and retrieval-augmented examples to fine-tuning, schema-constrained decoding, agent workflows, and verification against source evidence. Models can produce well-formed outputs, but accurate and complete values remain difficult in long, noisy, multimodal, or specialized documents, so evaluation, provenance, and human review remain central.

Latest papers

CardsList

248 papers16 papers in the last four weeks, down 52% on the four weeks before. 0.1% of all new papers.

  1. Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction

    Jan 26, 2026Mikel Zubillaga, Oscar Sainz, Oier Lopez de Lacalle +1Self-Consistency DecodingDocument Information Extraction

  2. Assessment of Generative Named Entity Recognition in the Era of Large Language Models

    Jan 25, 2026Qi Zhan, Yile Wang, Hui HuangNamed Entity RecognitionLLM Information Extraction

  3. Strategies for Span Labeling with Large Language Models

    Jan 23, 2026Danil Semin, Ondřej Dušek, Zdeněk KasnerConstrained DecodingLanguage Model Decoding

  4. Rep2Text: Decoding Full Text from a Single LLM Token Representation

    Nov 9, 2025Haiyan Zhao, Zirui He, Yiming Tang +4LLM InterpretabilityLLM Information Extraction

  5. LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature

    Oct 28, 2025Magdalena Lederbauer, Siddharth Betala, Valerie Gentzke +22Document Information ExtractionMaterials Science

  6. Auditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5

    Oct 8, 2025Shrestha Ghosh, Luca Giordano, Yujia Hu +2Factual Knowledge in Language ModelsLLM Auditing

  7. GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge

    Jul 8, 2025Yujia Hu, Tuan-Phong Nguyen, Shrestha Ghosh +2KG ConstructionLLM Information Extraction

  8. Towards Large Language Models for Lunar Mission Planning and In Situ Resource Utilization

    Apr 28, 2025Michael Pekala, Gregory Canal, Samuel Barham +5LLM Information Extraction