@inproceedings{luo-sun-2025-ji,
    title = "基于思维链和知识迁移的多语言问答推理研究",
    author = "Luo, Jian  and
      Sun, Yuan",
    editor = "Sun, Maosong  and
      Duan, Peiyong  and
      Liu, Zhiyuan  and
      Xu, Ruifeng  and
      Sun, Weiwei",
    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-1.14/",
    pages = "170--183",
    abstract = "``近年来,大型语言模型如ChatGPT显著提高了机器对自然语言的理解能力,其中,问答推理任务在推动语言理解能力和人机交互智能化方面具有重要意义,但目前仍面临诸多挑战。本文针对现有大模型资源消耗大、小模型推理能力弱,低资源语言推理能力受限等问题,提出了融合思维链和微调技术的方法,通过Human-Thinking提示策略优化大模型推理能力,并借助大模型指令微调提升小模型推理性能,引入多角色协作机制进一步优化推理步骤质量。通过探索跨语言思维链提示方法,利用高资源语言知识弥补低资源语言不足,采用双通道机制和投票打分机制整合不同语言推理知识,提升模型在低资源语言的推理表现。实验结果表明,本文方法能有效提升小型模型在多语言问答推理的能力,具有一定的研究价值。''"
}