@inproceedings{wang-etal-2025-ccl25,
    title = "{CCL}25-Eval任务四系统报告:基于{RAG}与谓词相似性方法的叙实性检测智能体",
    author = "Wang, Yu  and
      Qian, Yang  and
      Liang, Ke  and
      Yang, Yiheng  and
      Yu, Zhai  and
      Huang, Chu-Ren",
    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-2.18/",
    pages = "152--156",
    abstract = "``本文聚焦于{``}叙实性推理{''}任务,即判断语言中事件真实性的语义理解能力。该任务不依赖外部知识,而基于语言结构本身进行推理,对当前大语言模型(LLMs)提出挑战。为解决模型在叙实性漂移、多义词处理等方面的不足,作者提出一种结合RAG(检索增强生成)与谓词相似性的方法,构建了一个融合参数化与非参数化知识的叙实性检测智能体系统。该系统通过分步提示与知识库支持,实现了更高的一致性、准确性与可解释性,在评测任务中取得了0.9240的稳健表现。''"
}