Evaluating Multilingual Capabilities of the Llama2 Language Model: Insights Beyond English-Centric Training

The performance of multilingual language models like Llama2 is not solely determined by the training data size, but also influenced by the choice of central language(s) used during training. Linguistic factors beyond just syntactic similarity, such as phonology and inventory, can also significantly impact translation quality, especially for languages not directly encountered during training.