@inproceedings{ducel-etal-2026-benchmarks,
    title = "Are Benchmarks a Source of Bias in {LLM}s? {MMLU}, {C}ommon{S}ense{QA} and {MGSM} under the Microscope",
    author = {Ducel, Fanny  and
      Shariff, Shayan Ahmed  and
      Al Kotob, Ibrahim  and
      Arakkal Remesh, Binesh  and
      Digoin-Caparros, Lucie  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Fort, Kar{\"e}n},
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.768/",
    pages = "17826--17841",
    ISBN = "979-8-89176-459-0"
}