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 existing 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.
@article{arxiv.2504.15120,
title = {Kuwain 1.5B: An Arabic SLM via Language Injection},
author = {Khalil Hennara and Sara Chrouf and Mohamed Motaism Hamed and Zeina Aldallal and Omar Hadid and Safwan AlModhayan},
journal= {arXiv preprint arXiv:2504.15120},
year = {2025}
}