@inproceedings{rosenthal-etal-2026-unexplored,
    title = "Unexplored flaws in multiple-choice {VQA} make benchmarking unreliable",
    author = {Rosenthal, Fabio  and
      Schmidt, Sebastian  and
      Graf, Dr. Thorsten  and
      Bagdonat, Thorsten  and
      G{\"u}nnemann, Stephan  and
      Schwinn, Leo},
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.162/",
    pages = "3412--3451",
    ISBN = "979-8-89176-462-0"
}