Abstract
"本文研究了利用大语言模型进行谓词引导的叙实性推理任务。在不微调场景下,针对Gemini 2.5 Pro模型,我们构建了基于谓词类型的思维链(CoT)提示,并创新性地让模型学习整个带答案的样本集以归纳宏观模式和规则,最终形成高效的提示词模板。在微调场景下,我们选用Qwen3-32b模型,利用llama factory进行LoRA微调,并使用llama.cpp完成模型向gguf格式的转换、量化及Ollama部署。实验结果展示了所提方法的有效性,其中在不微调赛道上,基于宏观模式提示的方法取得了94.01%的准确率;在微调赛道上,基于微调模型的系统取得了92.61%的准确率。"
- Anthology ID:
- 2025.ccl-2.14
- 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:
- 118–127
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.14/
- DOI:
- Bibkey:
- Cite (ACL):
- Zequn Li, Yuanhao Zhong, and Chengliang Chai. 2025. CCL25-Eval任务四系统报告:宏观模式提示与高效微调在叙实性推理中的应用. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 118–127, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- CCL25-Eval任务四系统报告:宏观模式提示与高效微调在叙实性推理中的应用 (Li et al., CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.14.pdf