作者位次 #4/6ACL 2026Findings· Findings of ACL
Stop Guessing When to Stop Testing: Efficient Model Evaluation with Just Enough Data
Ofir Arviv · Kristjan Greenewald · Yotam Perlitz · Hadar Mulian · Michal Shmueli-Scheuer · Leshem Choshen
摘要
The inherent rigidity of fixed-size benchmarks makes them an inefficient tool for model evaluation. Diverse evaluation objectives, including model ranking, model selection and testing throughout development, demand varying levels of statistical power. The mismatch between fixed sample sizes and t...