@inproceedings{berdichevsky-etal-2026-dream,
    title = "Dream at {S}em{E}val-2026 Task 13: {SALSA} for Single-Pass Machine-Generated Code Detection",
    author = "Berdichevsky, Ruslan  and
      Nahum-Gefen, Shai  and
      Ben-Zaken, Elad",
    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-1.52/",
    pages = "354--360",
    ISBN = "979-8-89176-414-9",
    abstract = "Large language models have transformed code generation, raising concerns around authorship, assessment integrity, and software trust. SemEval-2026 Task 13 Subtask A operationalizes detection as binary classification over code snippets, with a particular emphasis on out-of-distribution (OOD) generalization across unseen programming languages and application domains. We propose a SALSA-style formulation, Single-pass Autoregressive LLM Structured Classification, that maps each class to a dedicated output token and trains the model to emit a single-token label in a structured response. Rather than engineering hand-crafted features or decision rules, this formulation delegates the authorship decision to the model. To improve OOD robustness, we combine balanced sampling across languages with parameter-efficient fine-tuning and conservative training (low learning rate, single epoch) to avoid overfitting to the training domain. Our best system achieves OOD F1 = 0.789 on the official leaderboard, substantially outperforming the CodeBERT baseline (F1 = 0.305)."
}