@inproceedings{shao-etal-2024-balanced,
    title = "Balanced Data Sampling for Language Model Training with Clustering",
    author = "Shao, Yunfan  and
      Li, Linyang  and
      Fei, Zhaoye  and
      Yan, Hang  and
      Lin, Dahua  and
      Qiu, Xipeng",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.833/",
    doi = "10.18653/v1/2024.findings-acl.833",
    pages = "14012--14023"
}