A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction

arXiv:2402.13364v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to specific structured formats, which is crucial in applications like named entity recognition (NER) or relation extraction (RE). To address this issue, this paper introduces an efficient method, G&O, to enhance their structured text generation capabilities. It breaks the generation into a two-step pipeline: initially, LLMs …

abstract applications arxiv cs.cl cs.ir extraction information information extraction language language model language models large language large language models llms natural natural language performance simple text type unstructured