@inproceedings{fan-etal-2024-nphardeval,
    title = "{NPH}ard{E}val: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes",
    author = "Fan, Lizhou  and
      Hua, Wenyue  and
      Li, Lingyao  and
      Ling, Haoyang  and
      Zhang, Yongfeng",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-long.225/",
    doi = "10.18653/v1/2024.acl-long.225",
    pages = "4092--4114"
}