GLiNER: Generalist Model for Named Entity Recognition Using Bidirectional Transformer

GLiNER is an open-source Named Entity Recognition (NER) model using a bidirectional transformer encoder, designed to improve efficiency, scalability, and multilingual performance while maintaining accuracy. It outperforms both ChatGPT and fine-tuned LLMs like UniNER in zero-shot evaluations across various NER benchmarks, including those in multiple languages. GLiNER's architecture is effective across different BiLMs (Bidirectional Language Models) and achieves strong performance with smaller model sizes than large LLMs. Its ability to generalize across various domains and languages makes it a promising solution for scenarios with limited labeled data.