Abstract
"本文面向CCL2025-Eval任务9中的中医辨证辨病与中药处方推荐两个子任务,提出了一套基于大语言模型的系统性方法。在子任务1中,本文基于QLoRA方法对Qwen2.5-7B、Mistral-7B和Baichuan-7B三种预训练模型进行高效微调,并引入多模型集成投票策略。在子任务串中,本文设计了融合向量检索、监督微调与强化学习的中药推荐框架,通过相似度检索构建候选处方集合,并利用强化学习优化模型的生成能力。最终在评测中获得总分0.5171(Task1得分0.5710,Task2得分0.4632),排名第四,验证了所提方法的有效性与实用性。"
- Anthology ID:
- 2025.ccl-2.42
- 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:
- 355–362
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.42/
- DOI:
- Bibkey:
- Cite (ACL):
- Yiyang Kang, Yao Jiaqi, Tengxiao Lv, Bo Xu, Ling Luo, Yuanyuan Sun, and Hongfei Lin. 2025. CCL25-Eval任务9系统报告:一种面向中医辨证与处方生成任务的检索增强大模型方法. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 355–362, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- CCL25-Eval任务9系统报告:一种面向中医辨证与处方生成任务的检索增强大模型方法 (Kang et al., CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.42.pdf