@inproceedings{xing-etal-2026-ynu,
    title = "{YNU}-{HPCC} at {S}em{E}val-2026 Task 13: Robust Machine-Generated Code Detection under Distribution Shifts",
    author = "Xing, Lixian  and
      Wang, Jin  and
      Zhang, Xuejie",
    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-1.205/",
    pages = "1582--1590",
    ISBN = "979-8-89176-414-9",
    abstract = "As Large Language Models (LLMs) become prevalent in software development, distinguishing machine-generated from human-written code is increasingly important. This paper describes the system developed by the YNU-HPCC team for SemEval-2026 Task 13, which evaluates detection under cross-language, multi-generator, and hybrid settings. Three modeling paradigms are systematically examined: encoder-based fine-tuning, feature-based machine learning, and task-specific robustness strategies. For Subtask A (Binary Detection), frozen pre-trained encoders and shallow stylometric features exhibit stronger cross-domain robustness than full fine-tuning, with indentation entropy identified as a key discriminative signal. For Subtask B (Multi-Class Attribution), a hierarchical two-stage framework is adopted to decouple human{--}machine discrimination from fine-grained generator attribution, alleviating severe class imbalance. For Subtask C (Hybrid Detection), a token-level splicing augmentation strategy combined with Supervised Contrastive Learning and Focal Loss is employed to model intra-sample stylistic variation. According to the official leaderboard, our system ranked 12th out of 81 teams in Subtask A, 14th out of 34 in Subtask B, and 8th out of 32 in Subtask C."
}