@inproceedings{dai-etal-2026-demystifying,
    title = "Demystifying Data Organization for Enhanced {LLM} Training",
    author = "Dai, Yalun  and
      Huang, Yangyu  and
      Yang, Tongshen  and
      Wang, Yonghan  and
      Zhang, Xin  and
      Wu, Wenshan  and
      Zhao, Qihao  and
      Li, Hao  and
      Gao, Yuanyuan  and
      Yap, Kim-Hui  and
      Li, Scarlett",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1262/",
    pages = "27358--27375",
    ISBN = "979-8-89176-390-6"
}