AI RESEARCH
Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages
arXiv CS.CL
•
ArXi:2605.04208v1 Announce Type: new Large language models (LLMs) have nstrated impressive multilingual capabilities for well-resourced languages, yet their performance on low-resource African languages remains poorly understood and largely unevaluated. This paper presents Nsanku, a systematic benchmark that evaluates the zero-shot machine translation performance of 19 open-weight and