Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ

arXiv:2403.03814v1 Announce Type: new
Abstract: Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. However, most LLMs today, and open LLMs in particular, are often intended for use in just English (e.g. Llama2, Mistral) or a small handful of high-resource languages (e.g. Mixtral, Qwen). Recent research shows that, despite limits in their intended use, people prompt LLMs in many different languages. Therefore, in this paper, we investigate the basic multilingual capabilities of state-of-the-art open …

abstract arxiv capabilities cs.ai cs.cl elementary english global however language language models languages large language large language models llama2 llms mistral mixtral multilingual serve small speakers type