2025
Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments
Tuka Alhanai, Adam Kasumovic, Mohammad M. Ghassemi, Aven Zitzelberger, Jessica M. Lundin, Guillaume Chabot-Couture
AAAI 2025technical
Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchma…