@inproceedings{wang-etal-2024-mmlu,
    title = "{MMLU}-{SR}: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models",
    author = "Wang, Wentian  and
      Jain, Sarthak  and
      Kantor, Paul  and
      Feldman, Jacob  and
      Gallos, Lazaros  and
      Wang, Hao",
    editor = "Hupkes, Dieuwke  and
      Dankers, Verna  and
      Batsuren, Khuyagbaatar  and
      Kazemnejad, Amirhossein  and
      Christodoulopoulos, Christos  and
      Giulianelli, Mario  and
      Cotterell, Ryan",
    booktitle = "Proceedings of the 2nd GenBench Workshop on Generalisation (Benchmarking) in NLP",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.genbench-1.5/",
    doi = "10.18653/v1/2024.genbench-1.5",
    pages = "69--85"
}