@inproceedings{li-etal-2026-beyond-output-correctness,
    title = "Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks",
    author = "Li, Yuangang  and
      Chen, Justin Tian Jin  and
      Yu, Ethan  and
      Hong, David  and
      Ahmed, Iftekhar",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.680/",
    pages = "15666--15689",
    ISBN = "979-8-89176-459-0"
}