@inproceedings{belz-etal-2026-shared,
    title = "The Shared Task on Reproducibility of Evaluations in {NLP} ({R}epro{NLP}) 2026: Overview and Results",
    author = "Belz, Anya  and
      Thomson, Craig  and
      Gonz{\'a}lez Corbelle, Javier",
    editor = "Mille, Simon  and
      Gehrmann, Sebastian  and
      Schmidtov{\'a}, Patr{\'i}cia  and
      Du{\v{s}}ek, Ond{\v{r}}ej  and
      Fadaee, Marzieh  and
      Lo, Kyle  and
      Santus, Enrico  and
      Stanovsky, Gabriel",
    booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.gem-main.83/",
    pages = "1055--1070",
    ISBN = "979-8-89176-423-1",
    abstract = "We present the 2026 Shared Task on Reproducibility of Evaluations in NLP (ReproNLP{'}26) which followed on from five predecessor shared tasks on reproducibility of evaluations, ReproNLP{'}25, 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{'}26 shared task, summarise results from the reproduction studies submitted, and provide additional comparative analysis of their results."
}