{"ID":2890984,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18546","arxiv_id":"2507.18546","title":"GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface","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.","short_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...","url_abs":"https://arxiv.org/abs/2507.18546","url_pdf":"https://arxiv.org/pdf/2507.18546v1","authors":"[\"Urchade Zaratiana\",\"Gil Pasternak\",\"Oliver Boyd\",\"George Hurn-Maloney\",\"Ash Lewis\"]","published":"2025-07-24T16:11:14Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611833,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2890984,"paper_url":"https://arxiv.org/abs/2507.18546","paper_title":"GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface","repo_url":"https://github.com/fastino-ai/GLiNER2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}