@inproceedings{pei-shu-juan-etal-2025-hmum,
    title = "{HMUM}:面向仇恨模因检测的多阶段多模态理解模型",
    author = "裴淑娟, 裴淑娟  and
      Zuo, Jiali  and
      He, Le  and
      Wan, Jianyi  and
      Wang, Mingwen",
    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-1.59/",
    pages = "783--791",
    abstract = "``随着社交媒体的广泛普及,模因(meme)已成为信息传播与舆论引导的重要载体,其中蕴含的仇恨内容对网络生态与公共安全构成威胁,尤其是通过图像暗示、文化隐喻或社会符号等方式表达的隐性仇恨模因,具有更强的隐蔽性与误导性,给仇恨模因检测任务带来显著挑战。针对上述问题,本文提出了一种仇恨模因理解模型(Hateful Meme Understanding Model,HMUM),在Qwen2.5-VL-72B-Instruct模型基础上引入LoRA微调,并设计了一种多模态多阶段的提示学习框架。该框架通过阶段性引导模型依次完成文本识别、情绪建模与仇恨性推理,逐步增强其对模因语义与情感的理解能力,从而有效提升模型在中文语境下检测语义隐晦、情绪复杂仇恨模因的准确性。在公开数据集ToxiCN MM上的实验结果表明,HMUM(Qwen)在整体任务中取得了显著性能提升,在隐性仇恨模因子集检测方面,相较于基线模型表现出更强的优势。为评估其在更广泛隐性场景中的检测能力,本文构建了以隐性仇恨模因为主的数据集ITTD-220,实验结果显示,HMUM(Qwen)在该数据集上的检测性能同样优于现有模型,验证了其出色的泛化能力。''"
}