ADELIE: Aligning Large Language Models on Information Extraction

arXiv:2405.05008v1 Announce Type: new
Abstract: Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect …

abstract alignment arxiv cs.cl data datasets extraction humans information information extraction language language models large language large language models llms paper struggle tasks type