@inproceedings{zuo-etal-2026-speak,
    title = "Speak No Evil, Just Prompt: Low-resource Multilingual Toxic Speech Detection with Audio Language Model",
    author = "Zuo, Mingzi  and
      Zhang, Lei  and
      Sun, Hailiang  and
      Huo, Shengzhi  and
      Dong, Changyu  and
      Wang, Xin  and
      Wang, Bo  and
      Liu, Hao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.439/",
    pages = "9039--9053",
    ISBN = "979-8-89176-395-1",
    abstract = "The widespread dissemination of toxic content on online platforms poses a critical threat to user experience. Toxicity detection in speech receives significantly less research attention than its text counterpart. Most existing methods rely on high-resource languages and employ a cascaded pipeline combining automatic speech recognition (ASR) and text classifiers. These designs limit robustness in low-resource languages and discard important acoustic cues. To address the lack of datasets, we construct PolySpeechTox, the first toxicity-annotated speech dataset spanning 53 languages and accent varieties, with a focus on low-resource languages and multiple accents. Based on PolySpeechTox, we conduct the first systematic study of toxic speech detection under low-resource, multilingual, and multi-accent conditions. We propose SoftPrompt-TSD, a prompt-based adaptation framework that leverages a frozen audio language model to perform end-to-end toxicity detection without ASR. The decomposed soft-prompt design balances global task alignment, cross-lingual generalization, and language-specific or accent-specific calibration. On PolySpeechTox, SoftPrompt-TSD achieves a micro-averaged ROC-AUC of 98.07{\%}, mitigating the severe failures observed in baseline methods for several languages. In three generalization experiments, SoftPrompt-TSD demonstrates superior generalization capability and maintains robust performance against distribution shifts."
}