@inproceedings{shang-etal-2025-nile,
    title = "Nile-Chat: {E}gyptian Language Models for {A}rabic and {L}atin Scripts",
    author = "Shang, Guokan  and
      Abdine, Hadi  and
      Chamma, Ahmad  and
      Mohamed, Amr  and
      Anwar, Mohamed  and
      Bounhar, Abdelaziz  and
      El Herraoui, Omar  and
      Nakov, Preslav  and
      Vazirgiannis, Michalis  and
      Xing, Eric P.",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.arabicnlp-main.25/",
    pages = "306--322",
    ISBN = "979-8-89176-352-4",
    abstract = "We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts. Specifically, with Nile-Chat-3x4B-A6B, we introduce a novel language adaptation approach by leveraging the Branch-Train-MiX strategy to merge script-specialized experts, into a single MoE model. Our Nile-Chat models significantly outperform leading multilingual and Arabic LLMs, such as LLaMa, Jais, and ALLaM, on our newly introduced Egyptian evaluation benchmarks, which span both understanding and generative tasks. Notably, our 12B model delivers a 14.4{\%} performance gain over Qwen2.5-14B-Instruct on Latin-script benchmarks. All our resources are publicly available. We believe this work presents a comprehensive methodology for adapting LLMs to a single language with dual-script usage, addressing an often overlooked aspect in contemporary LLM development."
}