Abstract
"中国古典诗词语言凝练、意境深远,对自然语言处理系统提出了严峻挑战。本次评测聚焦于古诗词理解与推理,包括词语释义、句子翻译和情感分析三项子任务。本文基于Qwen2.5-14B-Instruct 模型,在LLaMA Factory 框架下采用监督微调(SFT)与LoRA 参数高效微调策略,提升模型在few-shot 条件下的表现。训练数据来自官方发布的多类别JSON 格式语料,经整合与指令格式转换后用于模型训练。实验表明,LoRA 微调显著优于zero-shot 基线。本研究验证了参数高效微调方法在有限数据场景下的有效性。"
- Anthology ID:
- 2025.ccl-2.25
- Volume:
- Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
- Month:
- August
- Year:
- 2025
- Address:
- Jinan, China
- Editors:
- Hongfei Lin, Bin Li, Hongye Tan
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 206–211
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.25/
- DOI:
- Bibkey:
- Cite (ACL):
- Jue Wang. 2025. CCL25-Eval 任务5系统报告:基于千问大模型的古诗词理解与推理研究. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 206–211, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- CCL25-Eval 任务5系统报告:基于千问大模型的古诗词理解与推理研究 (Wang, CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.25.pdf