@inproceedings{renduchintala-etal-2023-ingenious,
    title = "{INGENIOUS}: Using Informative Data Subsets for Efficient Pre-Training of Language Models",
    author = "Renduchintala, H S V N S Kowndinya  and
      Killamsetty, Krishnateja  and
      Bhatia, Sumit  and
      Aggarwal, Milan  and
      Ramakrishnan, Ganesh  and
      Iyer, Rishabh  and
      Krishnamurthy, Balaji",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.findings-emnlp.445/",
    doi = "10.18653/v1/2023.findings-emnlp.445",
    pages = "6690--6705"
}