@inproceedings{arous-cheung-2026-reprohum,
    title = "{R}epro{H}um {\#}0033-05: Human Evaluation Report on ``Generating Scientific Definitions with Controllable Complexity''",
    author = "Arous, Ines  and
      Cheung, Jackie Chi Kit",
    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.89/",
    pages = "1117--1126",
    ISBN = "979-8-89176-423-1",
    abstract = "Human evaluation remains a central component of assessing NLG systems, especially for open-ended or creative generation tasks. Yet, the field still lacks standardized practices for designing and reporting such evaluations. In this paper, we present a reproduction study of the human evaluation conducted by August et al. for their method of generating scientific definitions with controllable complexity. By closely replicating their experimental setup, we find that our results partially align with the original findings, suggesting a moderate level of reproducibility."
}