@inproceedings{balepur-etal-2025-best,
    title = "Which of These Best Describes Multiple Choice Evaluation with {LLM}s? A) Forced {B}) Flawed {C}) Fixable {D}) All of the Above",
    author = "Balepur, Nishant  and
      Rudinger, Rachel  and
      Boyd-Graber, Jordan Lee",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.169/",
    pages = "3394--3418",
    ISBN = "979-8-89176-251-0"
}