How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design

Angelo Basile; Areg Mikael Sarvazyan; José-Ángel González

doi:10.63317/4j37zxirsi26

How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design

Angelo Basile, Areg Mikael Sarvazyan, José Ángel González

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

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.

Anthology ID:: 2026.lrec-1.353
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 4507–4513
Language:
External URL:: https://lrec.elra.info/lrec2026-main-353
DOI:: 10.63317/4j37zxirsi26
Bibkey:
Cite (ACL):: Angelo Basile, Areg Mikael Sarvazyan, and José Ángel González. 2026. How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4507–4513, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design (Basile et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{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",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.353/",
    doi = "10.63317/4j37zxirsi26",
    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."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basile-etal-2026-many">
    <titleInfo>
        <title>How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Angelo</namePart>
        <namePart type="family">Basile</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Areg</namePart>
        <namePart type="given">Mikael</namePart>
        <namePart type="family">Sarvazyan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">José</namePart>
        <namePart type="given">Ángel</namePart>
        <namePart type="family">González</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">basile-etal-2026-many</identifier>
    <identifier type="doi">10.63317/4j37zxirsi26</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.353/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>4507</start>
            <end>4513</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design
%A Basile, Angelo
%A Sarvazyan, Areg Mikael
%A González, José Ángel
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F basile-etal-2026-many
%X 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.
%R 10.63317/4j37zxirsi26
%U https://aclanthology.org/2026.lrec-1.353/
%U https://doi.org/10.63317/4j37zxirsi26
%P 4507-4513

Download as File

Markdown (Informal)

[How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design](https://aclanthology.org/2026.lrec-1.353/) (Basile et al., LREC 2026)

How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design (Basile et al., LREC 2026)

ACL

Angelo Basile, Areg Mikael Sarvazyan, and José Ángel González. 2026. How Many Samples Do We Need? A Toolkit for Power-Aware Evaluation Design. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 4507–4513, Palma de Mallorca, Spain. ELRA Language Resource Association.