@inproceedings{bunn-etal-2025-fine,
    title = "Fine-Tune on the Format: First Improving Multiple-Choice Evaluation for Intermediate {LLM} Checkpoints",
    author = "Bunn, Alec  and
      Wiegreffe, Sarah  and
      Bogin, Ben",
    editor = "Arviv, Ofir  and
      Clinciu, Miruna  and
      Dhole, Kaustubh  and
      Dror, Rotem  and
      Gehrmann, Sebastian  and
      Habba, Eliya  and
      Itzhak, Itay  and
      Mille, Simon  and
      Perlitz, Yotam  and
      Santus, Enrico  and
      Sedoc, Jo{\~a}o  and
      Shmueli Scheuer, Michal  and
      Stanovsky, Gabriel  and
      Tafjord, Oyvind",
    booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
    month = jul,
    year = "2025",
    address = "Vienna, Austria and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.gem-1.46/",
    pages = "511--521",
    ISBN = "979-8-89176-261-9"
}