MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks

arXiv:2404.00457v1 Announce Type: new
Abstract: Information extraction (IE) is a fundamental area in natural language processing where prompting large language models (LLMs), even with in-context examples, cannot defeat small LMs tuned on very small IE datasets. We observe that IE tasks, such as named entity recognition and relation extraction, all focus on extracting important information, which can be formalized as a label-to-span matching. In this paper, we propose a novel framework MetaIE to build a small LM as meta-model by …

abstract arxiv context cs.cl datasets examples extraction information information extraction language language models language processing large language large language models llm llms lms meta natural natural language natural language processing observe processing prompting recognition small tasks type