@inproceedings{anastasia-2026-gmail,
    title = "No{\_}gmail at {\#}{SMM}4{H}-{H}ea{RD} 2026: Detecting Patient Metadata in {COVID}-19 Scientific Literature: A Comparative Study of Encoder-Only and Autoregressive Language Models",
    author = "Anastasia, Stefanescu",
    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/acl-awards/2026.smm4h-1.46/",
    doi = "10.18653/v1/2026.smm4h-1.46",
    pages = "280--285",
    ISBN = "979-8-89176-432-3",
    abstract = "Identifying sentences in COVID-19 literature that report patient metadata is an important step in genomic epidemiology, currently requiring costly manual curation. We compare fine-tuned encoder-only models (BERT, BioLinkBERT) and autoregressive LLMs (Llama, Gemma, GPT-OSS) under prompting and fine-tuning regimes, using Focal Loss and undersampling to address severe class imbalance. Encoder-only models substantially outperform autoregressive models: BioLinkBERT-base with Focal Loss achieves macro F1 of 0.76, versus 0.54 for the best fine-tuned autoregressive model."
}