@inproceedings{muckatira-etal-2026-pre,
    title = "A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization",
    author = "Muckatira, Sherin  and
      Shivagunde, Namrata  and
      Deshpande, Vijeta  and
      Rumshisky, Anna",
    editor = "Zhang, Yue  and
      Xu, Ruifeng  and
      Purwarianti, Ayu  and
      Rong, Tong  and
      Suzuki, Jun",
    booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = nov,
    year = "2026",
    address = "Hengqin, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.aacl-long.213/",
    pages = "4761--4780",
    ISBN = "979-8-89176-439-2"
}