@inproceedings{jumelet-etal-2026-babybabellm,
    title = "{B}aby{B}abel{LM}: A Multilingual Benchmark of Developmentally Plausible Training Data",
    author = "Jumelet, Jaap  and
      Fourtassi, Abdellah  and
      Haga, Akari  and
      Bunzeck, Bastian  and
      Shandilya, Bhargav  and
      Galvan-Sosa, Diana  and
      Haznitrama, Faiz Ghifari  and
      Padovani, Francesca  and
      Meyer, Francois  and
      Hu, Hai  and
      Etxaniz, Julen  and
      Prevot, Laurent  and
      He, Linyang  and
      Grandury, Mar{\'i}a  and
      Marcheva, Mila  and
      Foroutan, Negar  and
      Theodoropoulos, Nikitas  and
      Sadeghi, Pouya  and
      Song, Siyuan  and
      Salhan, Suchir  and
      Zhou, Susana  and
      Paniv, Yurii  and
      Zhang, Ziyin  and
      Bisazza, Arianna  and
      Warstadt, Alex  and
      Choshen, Leshem",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.152/",
    pages = "3297--3329",
    ISBN = "979-8-89176-380-7",
    abstract = "We present BabyBabelLM, a multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. We curate developmentally plausible pretraining data aiming to cover the equivalent of 100M English words of content in each of 45 languages. We compile evaluation suites and train baseline models in each language. BabyBabelLM aims to facilitate multilingual pretraining and cognitive modeling."
}