@inproceedings{chen-etal-2024-good-data,
    title = "Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?",
    author = "Chen, Pinzhen  and
      Yu, Simon  and
      Guo, Zhicheng  and
      Haddow, Barry",
    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.542/",
    doi = "10.18653/v1/2024.emnlp-main.542",
    pages = "9706--9726"
}