Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT

TL;DR

This paper compares the performance of ChatGPT, Gemini, and LLaMA on zero-shot end-to-end relation extraction in Chinese, highlighting their strengths and limitations in accuracy and efficiency.

Contribution

It provides a comprehensive evaluation of LLMs for Chinese RE, an area previously underexplored, and offers insights into their practical trade-offs.

Findings

ChatGPT achieves the highest accuracy in Chinese RE.

Gemini offers the fastest inference speed.

LLaMA underperforms in accuracy and latency.

Abstract

This study investigates the performance of various large language models (LLMs) on zero-shot end-to-end relation extraction (RE) in Chinese, a task that integrates entity recognition and relation extraction without requiring annotated data. While LLMs show promise for RE, most prior work focuses on English or assumes pre-annotated entities, leaving their effectiveness in Chinese RE largely unexplored. To bridge this gap, we evaluate ChatGPT, Gemini, and LLaMA based on accuracy, efficiency, and adaptability. ChatGPT demonstrates the highest overall performance, balancing precision and recall, while Gemini achieves the fastest inference speed, making it suitable for real-time applications. LLaMA underperforms in both accuracy and latency, highlighting the need for further adaptation. Our findings provide insights into the strengths and limitations of LLMs for zero-shot Chinese RE, shedding light on trade-offs between accuracy and efficiency. This study serves as a foundation for future research aimed at improving LLM adaptability to complex linguistic tasks in Chinese NLP.