@inproceedings{arviv-etal-2026-stop, title = "Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data", author = "Arviv, Ofir and Greenewald, Kristjan and Perlitz, Yotam and Mulian, Hadar and Shmueli-Scheuer, Michal and Choshen, Leshem", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.43/", pages = "871--881", ISBN = "979-8-89176-395-1" }