@inproceedings{guo-etal-2025-lost,
    title = "Lost in Pronunciation: Detecting {C}hinese Offensive Language Disguised by Phonetic Cloaking Replacement",
    author = "Guo, Haotan  and
      He, Jianfei  and
      Ma, Jiayuan  and
      Na, Hongbin  and
      Wang, Zimu  and
      Zhang, Haiyang  and
      Chen, Qi  and
      Wang, Wei  and
      Shi, Zijing  and
      Shen, Tao  and
      Chen, Ling",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.172/",
    pages = "2538--2550",
    ISBN = "979-8-89176-333-3",
    abstract = "Phonetic Cloaking Replacement (PCR), defined as the deliberate use of homophonic or near-homophonic variants to hide toxic intent, has become a major obstacle to Chinese content moderation. While this problem is well-recognized, existing evaluations predominantly rely on rule-based, synthetic perturbations that ignore the creativity of real users. We organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 naturally occurring, phonetically cloaked offensive posts gathered from the RedNote platform. Benchmarking state-of-the-art LLMs on this dataset exposes a serious weakness: the best model reaches only an F1-score of 0.672, and zero-shot chain-of-thought prompting pushes performance even lower. Guided by error analysis, we revisit a Pinyin-based prompting strategy that earlier studies judged ineffective and show that it recovers much of the lost accuracy. This study offers the first comprehensive taxonomy of Chinese PCR, a realistic benchmark that reveals current detectors' limits, and a lightweight mitigation technique that advances research on robust toxicity detection."
}