@inproceedings{belz-etal-2025-2025,
title = "The 2025 {R}epro{NLP} Shared Task on Reproducibility of Evaluations in {NLP}: Overview and Results",
author = "Belz, Anya and
Thomson, Craig and
Gonz{\'a}lez Corbelle, Javier and
Ruelle, Malo",
editor = "Arviv, Ofir and
Clinciu, Miruna and
Dhole, Kaustubh and
Dror, Rotem and
Gehrmann, Sebastian and
Habba, Eliya and
Itzhak, Itay and
Mille, Simon and
Perlitz, Yotam and
Santus, Enrico and
Sedoc, Jo{\~a}o and
Shmueli Scheuer, Michal and
Stanovsky, Gabriel and
Tafjord, Oyvind",
booktitle = "Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM{\texttwosuperior})",
month = jul,
year = "2025",
address = "Vienna, Austria and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.gem-1.78/",
pages = "1002--1016",
ISBN = "979-8-89176-261-9",
abstract = "This paper presents an overview of, and the results from, the 2025 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP{'}25) which followed on from four previous shared tasks on reproducibility of evaluations, ReproNLP{'}24, ReproNLP{'}23, ReproGen{'}22 and ReproGen{'}21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of the topic across the two fields. We describe the ReproNLP{'}25 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results, including for the first time additional, `sanity-check' evaluations by LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belz-etal-2025-2025">
<titleInfo>
<title>The 2025 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">González Corbelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malo</namePart>
<namePart type="family">Ruelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ofir</namePart>
<namePart type="family">Arviv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miruna</namePart>
<namePart type="family">Clinciu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliya</namePart>
<namePart type="family">Habba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Itzhak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yotam</namePart>
<namePart type="family">Perlitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oyvind</namePart>
<namePart type="family">Tafjord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-261-9</identifier>
</relatedItem>
<abstract>This paper presents an overview of, and the results from, the 2025 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP’25) which followed on from four previous shared tasks on reproducibility of evaluations, ReproNLP’24, ReproNLP’23, ReproGen’22 and ReproGen’21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of the topic across the two fields. We describe the ReproNLP’25 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results, including for the first time additional, ‘sanity-check’ evaluations by LLMs.</abstract>
<identifier type="citekey">belz-etal-2025-2025</identifier>
<location>
<url>https://aclanthology.org/2025.gem-1.78/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1002</start>
<end>1016</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The 2025 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results
%A Belz, Anya
%A Thomson, Craig
%A González Corbelle, Javier
%A Ruelle, Malo
%Y Arviv, Ofir
%Y Clinciu, Miruna
%Y Dhole, Kaustubh
%Y Dror, Rotem
%Y Gehrmann, Sebastian
%Y Habba, Eliya
%Y Itzhak, Itay
%Y Mille, Simon
%Y Perlitz, Yotam
%Y Santus, Enrico
%Y Sedoc, João
%Y Shmueli Scheuer, Michal
%Y Stanovsky, Gabriel
%Y Tafjord, Oyvind
%S Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria and virtual meeting
%@ 979-8-89176-261-9
%F belz-etal-2025-2025
%X This paper presents an overview of, and the results from, the 2025 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP’25) which followed on from four previous shared tasks on reproducibility of evaluations, ReproNLP’24, ReproNLP’23, ReproGen’22 and ReproGen’21. This shared task series forms part of an ongoing research programme designed to develop theory and practice of reproducibility assessment in NLP and machine learning, against a backdrop of increasing recognition of the importance of the topic across the two fields. We describe the ReproNLP’25 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results, including for the first time additional, ‘sanity-check’ evaluations by LLMs.
%U https://aclanthology.org/2025.gem-1.78/
%P 1002-1016
Markdown (Informal)
[The 2025 ReproNLP Shared Task on Reproducibility of Evaluations in NLP: Overview and Results](https://aclanthology.org/2025.gem-1.78/) (Belz et al., GEM 2025)
ACL