@article{basile-etal-2026-many,
    title = "How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design",
    author = "Basile, Angelo  and
      Sarvazyan, Areg Mikael  and
      Gonz{\'a}lez, Jos{\'e} {\'A}ngel",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.353/",
    pages = "4507--4513",
    abstract = "If datasets are the telescopes of our field, then statistical power is their resolution, i.e., their ability to reveal a true difference in model performance when one exists. Many NLP evaluations are underpowered, leading to overstated claims of improvement. This paper introduces sk-power, an open-source Python library that helps researchers and practitioners design well-powered evaluations. Built with familiar scikit-learn-style abstractions, sk-power enables users to simulate evaluation scenarios, estimate minimum detectable effects, and assess the reliability of reported gains. We also illustrate what can go wrong when power analysis isn{'}t carried out. Our goal is to position power analysis as a first-class, practical step in evaluation planning."
}