CCiV: A Benchmark for Structure, Rhythm and Quality in LLM-Generated Chinese \textit{Ci} Poetry

TL;DR

This paper introduces CCiV, a comprehensive benchmark for evaluating large language models' ability to generate high-quality Chinese extit{Ci} poetry, focusing on structure, rhythm, and artistic quality, revealing key challenges and potential improvements.

Contribution

We present CCiV, the first benchmark specifically designed to evaluate LLMs on Chinese extit{Ci} poetry across multiple artistic and structural dimensions, and analyze model behaviors and limitations.

Findings

Models often produce valid but unexpected historical variants.

Adherence to tonal patterns is more difficult than structural rules.

Form-aware prompting improves control in stronger models but may harm weaker ones.

Abstract

The generation of classical Chinese \textit{Ci} poetry, a form demanding a sophisticated blend of structural rigidity, rhythmic harmony, and artistic quality, poses a significant challenge for large language models (LLMs). To systematically evaluate and advance this capability, we introduce \textbf{C}hinese \textbf{Ci}pai \textbf{V}ariants (\textbf{CCiV}), a benchmark designed to assess LLM-generated \textit{Ci} poetry across these three dimensions: structure, rhythm, and quality. Our evaluation of 17 LLMs on 30 \textit{Cipai} reveals two critical phenomena: models frequently generate valid but unexpected historical variants of a poetic form, and adherence to tonal patterns is substantially harder than structural rules. We further show that form-aware prompting can improve structural and tonal control for stronger models, while potentially degrading weaker ones. Finally, we observe weak and inconsistent alignment between formal correctness and literary quality in our sample. CCiV highlights the need for variant-aware evaluation and more holistic constrained creative generation methods.