@inproceedings{alnumay-etal-2025-command,
    title = "Command {R}7{B} {A}rabic: a small, enterprise-focused, multilingual, and culturally aware {A}rabic {LLM}",
    author = "Alnumay, Yazeed  and
      Barbet, Alexandre  and
      Bialas, Anna  and
      Darling, William Michael  and
      Shaan@cohere.com, Shaan@cohere.com  and
      Joan@cohere.com, Joan@cohere.com  and
      Duffy, Kyle  and
      Stephaniehowe@cohere.com, Stephaniehowe@cohere.com  and
      Lasche, Olivia  and
      Lee, Justin Seonyong  and
      Anirudh@cohere.com, Anirudh@cohere.com  and
      Jennifer@cohere.com, Jennifer@cohere.com",
    editor = "Lignos, Constantine  and
      Abdulmumin, Idris  and
      Adelani, David",
    booktitle = "Proceedings of the Sixth Workshop on African Natural Language Processing (AfricaNLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.africanlp-1.17/",
    pages = "126--135",
    ISBN = "979-8-89176-257-2",
    abstract = "Building high-quality large language models (LLMs) for enterprise Arabic applications remains challenging due to the limited availability of digitized Arabic data. In this work, we present a data synthesis and refinement strategy to help address this problem, namely, by leveraging synthetic data generation and human-in-the-loop annotation to expand our Arabic training corpus. We further present our iterative post training recipe that is essential to achieving state-of-the-art performance in aligning the model with human preferences, a critical aspect to enterprise use cases. The culmination of this effort is the release of a small, 7B, open-weight model that outperforms similarly sized peers in head-to-head comparisons and on Arabic-focused benchmarks covering cultural knowledge, instruction following, RAG, and contextual faithfulness."
}