This repository serves as a curated collection of academic papers focused on generative Information Extraction (IE) using Large Language Models (LLMs). It aims to provide researchers and practitioners with a comprehensive overview of the latest advancements, techniques, and datasets in this rapidly evolving field. The collection is organized by IE task (e.g., Named Entity Recognition, Relation Extraction, Event Extraction) and by technique (e.g., Few-shot learning, Prompt Design, Data Augmentation).

How It Works

The repository functions as a living bibliography, continuously updated with relevant research papers. It categorizes papers based on the specific Information Extraction task they address and the methodologies they employ. Each entry typically includes a link to the paper, venue, date, and often a code repository, facilitating easy access and reproducibility for users. The organization is guided by a comprehensive survey paper, "Large Language Models for Generative Information Extraction: A Survey," providing a structured framework for the collection.

Quick Start & Requirements

This is a curated list of papers and does not involve direct software installation or execution. Users can browse the collection via the GitHub repository.

Highlighted Details

• Comprehensive Coverage: Encompasses a wide range of IE tasks including NER, Relation Extraction, Event Extraction, and Universal IE.
• Technique-Centric Organization: Papers are categorized by key techniques like Few-shot learning, Prompt Design, Data Augmentation, and Constrained Decoding.
• Domain Specificity: Includes papers focusing on specific domains such as Biomedical, Scientific, Legal, and Multimodal IE.
• Regular Updates: The list is actively maintained, with recent papers added regularly, ensuring up-to-date coverage.

Maintenance & Community

The project is maintained by quqxui and welcomes contributions from the community. Users can submit requests for updates or report suggestions/mistakes via email. The primary contact emails are derongxu@mail.ustc.edu.cn and chenweicw@mail.ustc.edu.cn.

Licensing & Compatibility

The repository itself, as a collection of links and metadata, does not impose specific licensing restrictions on its use. However, users should adhere to the licenses of the individual papers and associated code repositories they access.

Limitations & Caveats

This repository is a curated list and does not provide executable code or models. Access to the full content of the papers requires obtaining them separately, and the availability of code links varies per entry.