@inproceedings{pan-etal-2025-benchmarks,
    title = "When Benchmarks Talk: Re-Evaluating Code {LLM}s with Interactive Feedback",
    author = "Pan, Jane  and
      Shar, Ryan  and
      Pfau, Jacob  and
      Talwalkar, Ameet  and
      He, He  and
      Chen, Valerie",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1267/",
    pages = "24672--24700",
    ISBN = "979-8-89176-256-5"
}