Rethinking Negative Instances for Generative Named Entity Recognition

arXiv:2402.16602v1 Announce Type: new
Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities for generalizing in unseen tasks. In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema. In this work, we explore the potential enhancement of the existing methods by incorporating negative instances into training. Our experiments reveal that negative instances contribute to remarkable improvements by (1) introducing contextual …

abstract arxiv capabilities cs.cl domains generative improvement instances language language models large language large language models llms negative ner recognition schema tasks type via work