@inproceedings{ye-etal-2024-rotbench,
    title = "{R}o{TB}ench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning",
    author = "Ye, Junjie  and
      Wu, Yilong  and
      Gao, Songyang  and
      Huang, Caishuang  and
      Li, Sixian  and
      Li, Guanyu  and
      Fan, Xiaoran  and
      Zhang, Qi  and
      Gui, Tao  and
      Huang, Xuanjing",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.19/",
    doi = "10.18653/v1/2024.emnlp-main.19",
    pages = "313--333"
}