@inproceedings{burns-etal-2026-aleph,
    title = "Aleph-Alpha-{G}erman{W}eb: Improving {G}erman-language {LLM} pre-training with model-based data curation and synthetic data generation",
    author = {Burns, Thomas F  and
      Parcalabescu, Letitia  and
      Waeldchen, Stephan  and
      Barlow, Michael  and
      Ziegltrum, Gregor  and
      Stampa, Volker  and
      Harren, Bastian  and
      Deiseroth, Bj{\"o}rn},
    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.58/",
    pages = "1267--1283",
    ISBN = "979-8-89176-380-7"
}