@inproceedings{langner-2026-reprohum,
    title = "{R}epro{H}um {\#}0124-03: Reproducing Human Scores on Neural {REG} Models",
    author = "Langner, Maurice",
    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.86/",
    pages = "1094--1103",
    ISBN = "979-8-89176-423-1",
    abstract = "In the context of the ReproNLP{'}26 shared task, I report on a single-criterion reproduction study of a human evaluation experiment for neuralreferring expression generation models (Castro Ferreira et al., 2018a), which has already been reproduced once by Mahamood (2024)for the ReproHum 2024 shared task. The experiments reported on in this paper therefore seek to second the findings from both previousexperiments."
}