@inproceedings{allam-2026-limics,
    title = "Limics at {\#}{SMM}4{H}-{H}ea{RD} 2026: Uncertainty-Driven Prediction for {ADE} Detection in Social Media",
    author = "Allam, Nour",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.37/",
    pages = "230--236",
    ISBN = "979-8-89176-432-3",
    abstract = "This paper describes our system for the SMM4H-HeaRD 2026 Task 1: \textit{Detection of Adverse Drug Events in Multilingual and Multi-platform Social Media Posts}. We developed a two-stage pipeline combining a fine-tuned XLM-RoBERTa-large encoder-only model with a large language model for final decision on ambiguous cases. To handle complex linguistic boundaries, we explore explicitly training the encoder to treat ambiguity as a discrete third label to delegate those cases to the generative model. Although introducing the third label was associated with lower performance than relying on a binary model, when using the encoder as a preliminary filter for classifying 78.62{\%} of posts as negatives, we achieved a global $F_1$ score of 0.614 (+0.034 over task median)."
}