@inproceedings{guillermo-etal-2026-thesis,
    title = "Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children{'}s Media",
    author = "Guillermo, Juliana Isabelle A.  and
      Catapang, Jasper Kyle  and
      Oco, Nathaniel",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-form-platform/2026.acl-srw.40/",
    pages = "450--462",
    ISBN = "979-8-89176-393-7",
    abstract = "Current automated content moderation systems fail to protect children from harmful YouTube content, particularly in under-resourced, code-switched settings. These systems are often text-only, English-centric, and operate as `black boxes,' lacking the multimodal understanding and transparency needed for effective moderation. This thesis proposes a novel hybrid framework for the explainable multimodal detection of harmful content in videos with code-switching. The proposed framework integrates a fine-tuned classifier for accurate, scalable detection with an LLM-powered module that synthesizes the classifier{'}s internal evidential signals (e.g., text attention and visual heat maps) to generate faithful, human-readable rationales for each decision. As a primary case study, the framework will be developed and validated on an English{--}Filipino code-switched dataset. Expected contributions include a new dataset publicly available under controlled access (de-identified transcripts, blacked-out frames, extracted feature representations, and metadata via data-sharing agreement) and a blueprint for building more equitable, transparent, and trustworthy AI safety systems."
}