@inproceedings{luo-etal-2025-antif,
    title = "{A}nt{IF}:大语言模型抗干扰能力评估",
    author = "Luo, Yajing  and
      Hou, Yutao  and
      Chen, Yun  and
      Chen, Guanhua",
    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-1.26/",
    pages = "335--362",
    abstract = "``本文提出了一种多智能体协同的干扰数据生成框架,旨在评测分析大语言模型在复杂干扰下的鲁棒性。该框架以数学领域为起点,逐步扩展至医学、法律、科学及通用场景,构建了涵盖拼写干扰、数字干扰、类型干扰与谣言干扰四类干扰的跨领域数据集AntIF,共计近5000条数据。在此基础上,本文对主流开源语言模型进行了系统的抗干扰能力评估,并结合不同的提示工程策略与模型微调方法,深入分析了AntIF 在提升模型鲁棒性方面的实际效果。''"
}