Adelani, David IfeoluwaZhuang, Jian YunOchieng, MillicentMukiibi, JonathanKabongo, SalomonStenetorp, Pontus2025-03-112025-03-112024-06-05Adelani, D. I., Ojo, J., Azime, I. A., Zhuang, J. Y., Alabi, J. O., He, X., ... & Stenetorp, P. (2024). Irokobench: A new benchmark for african languages in the age of large language models. arXiv preprint arXiv:2406.03368.https://doi.org/10.48550/arXiv.2406.03368https://nru.uncst.go.ug/handle/123456789/10104Despite the widespread adoption of Large language models (LLMs), their remarkable capabilities remain limited to a few high-resource languages. Additionally, many low-resource languages (\eg African languages) are often evaluated only on basic text classification tasks due to the lack of appropriate or comprehensive benchmarks outside of high-resource languages. In this paper, we introduce IrokoBench -- a human-translated benchmark dataset for 17 typologically-diverse low-resource African languages covering three tasks: natural language inference~(AfriXNLI), mathematical reasoning~(AfriMGSM), and multi-choice knowledge-based question answering~(AfriMMLU). We use IrokoBench to evaluate zero-shot, few-shot, and translate-test settings~(where test sets are translated into English) across 10 open and six proprietary LLMs. Our evaluation reveals a significant performance gap between high-resource languages~(such as English and French) and low-resource African languages. We observe a significant performance gap between open and proprietary models, with the highest performing open model, Gemma 2 27B only at 63\% of the best-performing proprietary model GPT-4o performance. In addition, machine translating the test set to English before evaluation helped to close the gap for larger models that are English-centric, such as Gemma 2 27B and LLaMa 3.1 70B. These findings suggest that more efforts are needed to develop and adapt LLMs for African languages.enArticle