@inproceedings{g-etal-2026-team,
    title = "Team Duo at {S}em{E}val-2026 Task 13: Fine-tuning {C}ode{BERT} for Out-of-Distribution {AI}-Generated Code Detection",
    author = "G, Subhiksha  and
      M, Sanjai  and
      Sivanaiah, Rajalakshmi  and
      S, Angel Deborah",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.265/",
    pages = "2104--2107",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper addresses detecting AI-generated code in out-of-distribution settings by fine-tuning CodeBERT on algorithmic code from C++, Python, and Java. While the model achieves near-perfect performance on training data (F1 = 0.9935), it degrades significantly on unseen languages and domains (F1 = 0.3532). The high recall (0.8789) but low precision (0.2210) indicates over-prediction of machine-generated code. Error analysis reveals three failure modes: domain mismatch, unfamiliar syntax patterns, and insufficient training. Multi-epoch training and domain-specific augmentation are needed to improve OOD generalization."
}