Scholarlink

Large language models (LLMs), such as ChatGPT, have demonstrated remarkable abilities in simple information extraction tasks. However, when it comes to complex and demanding tasks like relation extraction (RE), LLMs may still have considerable space for improvement. In this paper, we extensively evaluate ChatGPT’s performance in RE to expose its strengths and limitations. We explore the design choices of ChatGPT’s input prompts for RE. Considering different combinations of these choices, we conduct thorough experiments on benchmark datasets and analyze ChatGPT’s comprehension abilities under different settings. Our experiment results provide insights for the future development of LLM-based RE models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Can ChatGPT Solve Relation Extraction? An Extensive Assessment via Design Choice Exploration

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Xinyi Wang,
  • Wenzheng Zhao,
  • Xiangrong Zhu,
  • Wei Hu

摘要

Large language models (LLMs), such as ChatGPT, have demonstrated remarkable abilities in simple information extraction tasks. However, when it comes to complex and demanding tasks like relation extraction (RE), LLMs may still have considerable space for improvement. In this paper, we extensively evaluate ChatGPT’s performance in RE to expose its strengths and limitations. We explore the design choices of ChatGPT’s input prompts for RE. Considering different combinations of these choices, we conduct thorough experiments on benchmark datasets and analyze ChatGPT’s comprehension abilities under different settings. Our experiment results provide insights for the future development of LLM-based RE models.