@inproceedings{sakai-etal-2024-toward,
    title = "Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates",
    author = "Sakai, Yusuke  and
      Nohejl, Adam  and
      Hang, Jiangnan  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    editor = "Belinkov, Yonatan  and
      Kim, Najoung  and
      Jumelet, Jaap  and
      Mohebbi, Hosein  and
      Mueller, Aaron  and
      Chen, Hanjie",
    booktitle = "Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.blackboxnlp-1.31/",
    doi = "10.18653/v1/2024.blackboxnlp-1.31",
    pages = "499--529"
}