GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface

TL;DR

GLiNER2 is a unified, efficient multi-task information extraction system that supports various NLP tasks within a single compact model, offering competitive performance and improved deployment accessibility.

Contribution

It extends the original GLiNER architecture to support multiple extraction tasks with a schema-driven interface, maintaining efficiency and compactness.

Findings

Competitive performance across extraction and classification tasks

Substantial improvements in deployment accessibility

Open-source release with pre-trained models

Abstract

Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expensive large language models. We present GLiNER2, a unified framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. Built pretrained transformer encoder architecture, GLiNER2 maintains CPU efficiency and compact size while introducing multi-task composition through an intuitive schema-based interface. Our experiments demonstrate competitive performance across extraction and classification tasks with substantial improvements in deployment accessibility compared to LLM-based alternatives. We release GLiNER2 as an open-source pip-installable library with pre-trained models and documentation at https://github.com/fastino-ai/GLiNER2.