@inproceedings{prins-etal-2026-model,
    title = "Is my model perplexed for the right reason? Contrasting {LLM}s' Benchmark Behavior with Token-Level Perplexity",
    author = {Prins, Zo{\"e}  and
      Punzo, Samuele  and
      Wildenburg, Frank  and
      Cin{\`a}, Giovanni  and
      Pezzelle, Sandro},
    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.110/",
    pages = "2584--2598",
    ISBN = "979-8-89176-459-0"
}