@inproceedings{tang-sun-2025-big,
    title = "Big Escape Benchmark: Evaluating Human-Like Reasoning in Language Models via Real-World Escape Room Challenges",
    author = "Tang, Zinan  and
      Sun, QiYao",
    editor = "Dhole, Kaustubh  and
      Clinciu, Miruna",
    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/corrections-2025-08/2025.gem-1.42/",
    pages = "488--503",
    ISBN = "979-8-89176-261-9"
}