@inproceedings{li-etal-2024-scalingfilter,
    title = "{S}caling{F}ilter: Assessing Data Quality through Inverse Utilization of Scaling Laws",
    author = "Li, Ruihang  and
      Wei, Yixuan  and
      Zhang, Miaosen  and
      Yu, Nenghai  and
      Hu, Han  and
      Peng, Houwen",
    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/jlcl-multiple-ingestion/2024.emnlp-main.187/",
    doi = "10.18653/v1/2024.emnlp-main.187",
    pages = "3209--3222"
}