Happy Buzaaba, a researcher at Princeton University, was among the co-authors of the NAACL 2025 Outstanding Paper Award-winning submission “IrokoBench: A new Benchmark for African Languages in the Age of Large Language Models.” IrokoBench is 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).