@inproceedings{beniwal-etal-2025-unityai,
    title = "{U}nity{AI} Guard: Pioneering Toxicity Detection Across Low-Resource {I}ndian Languages",
    author = "Beniwal, Himanshu  and
      Venkat, Reddybathuni  and
      Kumar, Rohit  and
      Srivibhav, Birudugadda  and
      Jain, Daksh  and
      Doddi, Pavan Deekshith  and
      Dhande, Eshwar  and
      Ananth, Adithya  and
      Kuldeep  and
      Singh, Mayank",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.33/",
    pages = "471--479",
    ISBN = "979-8-89176-334-0",
    abstract = "This work introduces UnityAI-Guard, a framework for binary toxicity classification targeting low-resource Indian languages. While existing systems predominantly cater to high-resource languages, UnityAI-Guard addresses this critical gap by developing state-of-the-art models for identifying toxic content across diverse Brahmic/Indic scripts. Our approach achieves an impressive average F1-score of 84.23{\%} across seven languages, leveraging a dataset of 567k training instances and 30k manually verified test instances. By advancing multilingual content moderation for linguistically diverse regions, UnityAI-Guard also provides public API access to foster broader adoption and application."
}