@inproceedings{li-etal-2025-hellaswag,
    title = "{H}ella{S}wag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of {LLM}s in Commonsense Reasoning",
    author = "Li, Xiaoyuan  and
      Li, Moxin  and
      Men, Rui  and
      Zhang, Yichang  and
      Bao, Keqin  and
      Wang, Wenjie  and
      Feng, Fuli  and
      Liu, Dayiheng  and
      Lin, Junyang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.472/",
    pages = "9038--9072",
    ISBN = "979-8-89176-256-5"
}