@inproceedings{phan-chiang-2025-mymy,
    title = "{M}y{M}y at {S}em{E}val-2025 Task 9: A Robust Knowledge-Augmented Data Approach for Reliable Food Hazard Detection",
    author = "Phan, Ben  and
      Chiang, Jung - Hsien",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.112/",
    pages = "812--822",
    ISBN = "979-8-89176-273-2",
    abstract = "Food hazard detection from web sources, including social media and official food agency websites, is crucial for mitigating economic and public health risks. However, challenges such as class imbalance and the need for transparent, explainable AI remain. To address these issues, we propose a Knowledge-Augmented Data approach using Retrieval-Augmented Generation (RAG) to improve food incident report classification in SemEval-2025 Task 9. Our method leverages domain-specific knowledge to enrich datasets and curate high-quality data, enhancing overall integrity. We hypothesize that knowledge-augmented data improves Macro-F1 scores, the primary evaluation metric. Our approach achieved a top-3 average ranking across both subtasks, demonstrating its effectiveness in advancing NLP applications for food safety and contributing to more reliable food hazard detection systems."
}