@inproceedings{kang-etal-2025-demystifying,
    title = "Demystifying Synthetic Data in {LLM} Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls",
    author = "Kang, Feiyang  and
      Ardalani, Newsha  and
      Kuchnik, Michael  and
      Emad, Youssef  and
      Elhoushi, Mostafa  and
      Sengupta, Shubhabrata  and
      Li, Shang-Wen  and
      Raghavendra, Ramya  and
      Jia, Ruoxi  and
      Wu, Carole-Jean",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.544/",
    pages = "10750--10769",
    ISBN = "979-8-89176-332-6"
}