Can ChatGPT Really Understand Modern Chinese Poetry?

arXiv cs.CL / 3/24/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

Key Points

  • The paper proposes a new, comprehensive evaluation framework to test whether ChatGPT can truly understand modern Chinese poetry rather than just generate or translate it.
  • It involves collaboration with professional poets to assess ChatGPT’s interpretations across multiple dimensions against the original poets’ intended meanings.
  • Results indicate alignment with the poets’ intents in over 73% of evaluated cases, suggesting meaningful comprehension in many aspects.
  • The study finds weaker performance in specific dimensions—especially capturing “poeticity,” implying limits in how well the model grasps stylistic/poetic qualities.
  • The authors claim the framework provides a foundation for future research on LLM understanding and for poetry-related applications.

Abstract

ChatGPT has demonstrated remarkable capabilities on both poetry generation and translation, yet its ability to truly understand poetry remains unexplored. Previous poetry-related work merely analyzed experimental outcomes without addressing fundamental issues of comprehension. This paper introduces a comprehensive framework for evaluating ChatGPT's understanding of modern poetry. We collaborated with professional poets to evaluate ChatGPT's interpretation of modern Chinese poems by different poets along multiple dimensions. Evaluation results show that ChatGPT's interpretations align with the original poets' intents in over 73% of the cases. However, its understanding in certain dimensions, particularly in capturing poeticity, proved to be less satisfactory. These findings highlight the effectiveness and necessity of our proposed framework. This study not only evaluates ChatGPT's ability to understand modern poetry but also establishes a solid foundation for future research on LLMs and their application to poetry-related tasks.