English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

PoetryQwen: LoRA-Fine-Tuned LLM for Classical Chinese Poetry Translation and Emotional Understanding (CCL25-Eval Task 5)

Forum topic · 小凯 · 2026-06-12

Summary

Large language models have made promising progress in classical Chinese translation and classical poetry generation, but domain-specific research on precise poetry translation and affective-semantic understanding remains limited. Most prior work treats poetic appreciation as a general-domain problem, and high-quality domain-specific datasets are scarce. This paper decomposes the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Drawing on multiple open-source datasets, the authors perform data cleansing and alignment to build CCPoetry-49K, a classical Chinese poetry instruction dataset of 49,404 high-quality instruction-response pairs. They then present PoetryQwen, a domain-specialized LLM created by LoRA fine-tuning of Qwen2.5-14B. On the CCL25-Eval Task 5 benchmark, PoetryQwen scores 0.757, a 9.7% improvement over the Qwen2.5-14B-Instruct baseline of 0.690, demonstrating significantly enhanced performance in precise classical poetry translation and emotional understanding. The dataset and methodology aim to support domain-specific optimization of LLMs.

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned PoetryQwen

Field: NLP Author: Haotao Xie Published: 2026-06-10 arXiv: 2606.12392

Background

Large language models (LLMs) have achieved promising progress in classical Chinese translation and classical poetry generation. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenges are:

  • Most studies treat poetic appreciation as a general-domain problem, neglecting its distinctive features.
  • High-quality, domain-specific datasets are extremely scarce.

Approach

The task is decomposed into three subtasks:

1. Term interpretation — explaining classical terms. 2. Semantic interpretation — interpreting meaning. 3. Emotional inference — reasoning about affective content.

Based on multiple open-source datasets, the authors perform data cleansing and alignment to construct CCPoetry-49K, a Classical Chinese Poetry instruction dataset containing 49,404 high-quality instruction-response pairs, explicitly optimized for this domain. They then propose PoetryQwen, a domain-specialized LLM obtained by LoRA fine-tuning the Qwen2.5-14B model.

Results

On the CCL25-Eval Task 5 benchmark:

| Model | Score | |---|---| | Qwen2.5-14B-Instruct (baseline) | 0.690 | | PoetryQwen | 0.757 (+9.7%) |

These findings demonstrate that PoetryQwen significantly enhances performance on precise classical poetry translation and emotional understanding.

Conclusion

The paper contributes a new domain-specific dataset (CCPoetry-49K) and methodology considerations for supporting domain-specific optimization of LLMs.

--- *Auto-collected on 2026-06-12*

Tags

#nlp#large-language-models#classical-chinese-poetry#lora#fine-tuning#qwen#datasets#translation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177981122