ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models

TL;DR

ChatUIE leverages large language models and reinforcement learning to enhance domain-specific information extraction from natural language, addressing limitations of previous prompt-based methods and improving extraction accuracy.

Contribution

This paper introduces ChatUIE, a unified information extraction framework based on ChatGLM, employing reinforcement learning and generation constraints for improved performance.

Findings

Significant improvement in information extraction accuracy.

Slight decrease in general chatting ability.

Effective handling of complex and limited samples.

Abstract

Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information from natural language that deviates from known schemas or instructions has proven challenging for previous prompt-based methods. This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language. In this paper, we present ChatUIE, an innovative unified information extraction framework built upon ChatGLM. Simultaneously, reinforcement learning is employed to improve and align various tasks that involve confusing and limited samples. Furthermore, we integrate generation constraints to address the issue of generating elements that are not present in the input. Our experimental results demonstrate that ChatUIE can significantly improve the performance of information extraction with a slight decrease in chatting ability.