ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models
This work addresses the challenge of domain-specific information extraction for users needing structured data from text, though it appears incremental as it builds on existing models like ChatGLM.
The authors tackled the problem of extracting structured information from natural language using large language models, particularly when dealing with unknown schemas or instructions, by developing ChatUIE, a chat-based unified information extraction framework built on ChatGLM. Their results show that ChatUIE significantly improves information extraction performance with only a slight decrease in chatting ability.
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.