An Empirical Study on Information Extraction using Large Language Models

TL;DR

This paper evaluates GPT-4's information extraction capabilities, identifies performance gaps compared to SOTA methods, and explores prompt-based techniques to enhance LLMs' extraction performance through extensive experiments.

Contribution

It provides a comprehensive assessment of GPT-4's IE ability and introduces prompt-based methods to improve LLMs' extraction performance, highlighting remaining challenges.

Findings

GPT-4 lags behind SOTA IE methods in performance.

Prompt-based techniques can improve GPT-4's IE ability.

Remaining issues suggest further research is needed.

Abstract

Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI's GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types. Our results suggest a visible performance gap between GPT-4 and state-of-the-art (SOTA) IE methods. To alleviate this problem, considering the LLMs' human-like characteristics, we propose and analyze the effects of a series of simple prompt-based methods, which can be generalized to other LLMs and NLP tasks. Rich experiments show our methods' effectiveness and some of their remaining issues in improving GPT-4's information extraction ability.