GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect

TL;DR

GIELLM is a pioneering Japanese LLM that unifies multiple information extraction tasks using mutual reinforcement, achieving state-of-the-art results and reducing the need for specialized models.

Contribution

It introduces the first model to handle diverse IE subtasks simultaneously with mutual reinforcement, demonstrating significant performance improvements.

Findings

Achieves SOTA in five out of six Japanese IE datasets.

Outperforms GPT-3.5-Turbo in integrated IE tasks.

Validates the effectiveness of mutual reinforcement in IE tasks.

Abstract

Information Extraction (IE) stands as a cornerstone in natural language processing, traditionally segmented into distinct sub-tasks. The advent of Large Language Models (LLMs) heralds a paradigm shift, suggesting the feasibility of a singular model addressing multiple IE subtasks. In this vein, we introduce the General Information Extraction Large Language Model (GIELLM), which integrates text Classification, Sentiment Analysis, Named Entity Recognition, Relation Extraction, and Event Extraction using a uniform input-output schema. This innovation marks the first instance of a model simultaneously handling such a diverse array of IE subtasks. Notably, the GIELLM leverages the Mutual Reinforcement Effect (MRE), enhancing performance in integrated tasks compared to their isolated counterparts. Our experiments demonstrate State-of-the-Art (SOTA) results in five out of six Japanese mixed datasets, significantly surpassing GPT-3.5-Turbo. Further, an independent evaluation using the novel Text Classification Relation and Event Extraction(TCREE) dataset corroborates the synergistic advantages of MRE in text and word classification. This breakthrough paves the way for most IE subtasks to be subsumed under a singular LLM framework. Specialized fine-tune task-specific models are no longer needed.