@inproceedings{zhang-graf-2025-mathematical,
    title = "Mathematical Computation and Reasoning Errors by Large Language Models",
    author = "Zhang, Liang  and
      Graf, Edith",
    editor = "Wilson, Joshua  and
      Ormerod, Christopher  and
      Beiting Parrish, Magdalen",
    booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
    month = oct,
    year = "2025",
    address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
    publisher = "National Council on Measurement in Education (NCME)",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.aimecon-main.45/",
    pages = "417--424",
    ISBN = "979-8-218-84228-4",
    abstract = "We evaluate four LLMs (GPT-4o, o1, DeepSeek-V3, DeepSeek-R1) on purposely challenging arithmetic, algebra, and number-theory items. Coding final answers and step-level solutions correctness reveals performance gaps, improvement paths, and how accurate LLMs can strengthen mathematics assessment and instruction."
}