GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
HiTZ Center - Ixa University of the Basque Country (UPV/EHU) · HiTZ Basque Center for Language Technology - Ixa, University of the Basque Country UPV/EHU · HiTZ Center - Ixa, University of the Basque Country UPV/EHU · Universidad del País Vasco · University of the Basque Country (UPV/EHU)
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Large Language Models (LLMs) combined with instruction tuning have made significant progress when generalizing to unseen tasks. However, they have been less successful in Information Extraction (IE), lagging behind task-specific models. Typically, IE tasks are characterized by complex annotation guidelines which describe the task and give examples to humans. Previous attempts to leverage such information have failed, even with the largest models, as they are not able to follow the guidelines out-of-the-box. In this paper we propose GoLLIE (Guideline-following Large Language Model for IE), a model able to improve zero-shot results on unseen IE tasks by virtue of being fine-tuned to comply with annotation guidelines. Comprehensive evaluation empirically demonstrates that GoLLIE is able to generalize to and follow unseen guidelines, outperforming previous attempts at zero-shot information extraction. The ablation study shows that detailed guidelines is key for good results. Code, data and models will be made publicly available.