@inproceedings{berrayana-etal-2025-bias,
    title = "Are Bias Evaluation Methods Biased ?",
    author = "Berrayana, Lina  and
      Rooney, Sean  and
      Garc{\'e}s-Erice, Luis  and
      Giurgiu, Ioana",
    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://preview.aclanthology.org/nschneid-patch-1/2025.gem-1.22/",
    pages = "249--261",
    ISBN = "979-8-89176-261-9",
    abstract = "The creation of benchmarksto evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias, harmful behavior etc. Independent benchmarks adopt different approacheswith distinct data sets and evaluation methods. We investigate how robust such benchmarks are by using different approachesto rank a set of representative models for bias andcompare how similar are the overall rankings. We show that different but widely used bias evaluations methods result in disparate model rankings. We conclude with recommendations for the community in the usage of such benchmarks."
}