@inproceedings{kang-etal-2025-ccl25,
    title = "{CCL}25-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",
    author = "Kang, Yiyang  and
      Jiaqi, Yao  and
      Lv, Tengxiao  and
      Xu, Bo  and
      Luo, Ling  and
      Sun, Yuanyuan  and
      Lin, Hongfei",
    editor = "Lin, Hongfei  and
      Li, Bin  and
      Tan, Hongye",
    booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
    month = aug,
    year = "2025",
    address = "Jinan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/ingest-ccl/2025.ccl-2.42/",
    pages = "355--362",
    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。''"
}