@inproceedings{jenkins-2026-beyond,
    title = "Beyond Static Benchmarks: A Validity, Reliability, and Sociotechnical Framework for Evaluating {LLM}s in Deployment Contexts",
    author = "Jenkins, Ben",
    editor = "Akhtar, Mubashara  and
      Batzner, Jan  and
      Choshen, Leshem  and
      Ghosh, Avijit  and
      Gohar, Usman  and
      Mickel, Jennifer  and
      Pant, Ichhya  and
      Talat, Zeerak  and
      Lin, Michelle",
    booktitle = "Proceedings of the Workshop on Evaluating Evaluations ({E}val{E}val)",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.evaleval-1.30/",
    pages = "201--210",
    ISBN = "979-8-89176-429-3"
}