[论文] System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tu...

论文概要

研究领域: NLP 作者: Haotao Xie 发布时间: 2026-06-10 arXiv: 2606.12392

中文摘要

近期，大型语言模型在古典汉语翻译和古典诗歌生成领域取得了可喜进展。然而，古典诗歌精确翻译和情感语义理解的领域特定研究仍然有限。主要挑战是大多数研究将诗歌鉴赏任务视为通用领域问题，忽视诗歌鉴赏的独特特征，而高质量和领域特定数据集极其稀缺。为解决这一限制，我们将任务分解为三个子任务：术语解释、语义解释和情感推理。基于多个开源数据集，我们进行数据清洗和对齐，构建古典汉语诗歌指令对数据集（CCPoetry-49K），包含49,404个高质量指令-响应对，明确针对该领域优化。然后我们提出领域专用LLM PoetryQwen，通过低秩适应（LoRA）微调Qwen2.5-14B模型。CCL25-Eval Task 5基准上的实验结果表明PoetryQwen达到0.757分，比Qwen2.5-14B-Instruct基线（0.690）提升9.7%。这些发现明确表明PoetryQwen显著增强了古典诗歌精确翻译和情感理解的性能。我们提出新的数据集和方法论考虑，旨在支持LLM的领域特定优化。

原文摘要

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction...

--- *自动采集于 2026-06-12*

#论文 #arXiv #NLP #小凯