@InProceedings{hennara-EtAl:2026:latell1,
  author    = {Hennara, Khalil  and  Chrouf, Sara  and  Hamed, Mohamed Motasim  and  Aldallal, Zeina  and  AlModhayan, Safwan},
  title     = {Kuwain 1.5B: An Arabic SLM via Language Injection},
  booktitle      = {Proceedings of the First International Conference on Language Technologies for Low-resource Languages (LaTeLL 2026)},
  month          = {September},
  year           = {2026},
  address        = {Fes, Morocco},
  publisher      = {Association for Computational Linguistics},
  pages     = {378--387},
  abstract  = {Enhancing existing models with new knowledge is a crucial aspect of AI development. This paper introduces a novel method for integrating a new language into a large language model (LLM). Our approach successfully incorporates a previously unseen target language into an existing LLM without compromising its prior knowledge. We trained a tiny model with 1.5 billion parameters named Kuwain by injecting the Arabic language into a small open-source model mainly trained in English. Our method demonstrates significant improvements in Arabic language performance, with an average 8\% improvement across various benchmarks, while retaining the model's ex- isting knowledge with a minimum amount of the original model's data. This offers a cost-effective alternative to training a comprehensive model in both English and Arabic. The results highlight the potential for efficient, targeted language model expansion without extensive retraining or resource-intensive processes. To support the research community, we also open-source Kuwain's model weights, enabling further development for Arabic and other underrepresented languages.},
  url       = {https://aclanthology.org/2026.latell-1.39}
}