@inproceedings{khalili-etal-2025-evaluating,
    title = "Evaluating Intermediate Reasoning of Code-Assisted Large Language Models for Mathematics",
    author = "Khalili, Zena Al  and
      Howell, Nick  and
      Klakow, Dietrich",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    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://preview.aclanthology.org/corrections-2025-08/2025.gem-1.64/",
    pages = "741--758",
    ISBN = "979-8-89176-261-9"
}