@inproceedings{trevino25naacl,
    title = {Benchmarking Failures in Tool-Augmented Language Models},
    author = {Eduardo Treviño and Hugo Contant and James Ngai and Graham Neubig and Zora Zhiruo Wang},
    booktitle = {Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL)},
    address = {Albuquerque, USA},
    month = {April},
    url = {https://arxiv.org/abs/2503.14227},
    year = {2025}
}