Large language models (LLMs) implicitly learn to perform a range of language
tasks, including machine translation (MT). Previous studies explore aspects of
LLMs' MT capabilities. However, there exist a wide variety of languages for
which recent LLM MT performance has never before been evaluated. Without
published experimental evidence on the matter, it is difficult for speakers of
the world's diverse languages to know how and whether they can use LLMs for
their languages. We present the first experimental evidence for an expansive
set of 204 languages, along with MT cost analysis, using the FLORES-200
benchmark. Trends reveal that GPT models approach or exceed traditional MT
model performance for some high-resource languages (HRLs) but consistently lag
for low-resource languages (LRLs), under-performing traditional MT for 84.1% of
languages we covered. Our analysis reveals that a language's resource level is
the most important feature in determining ChatGPT's relative ability to
translate it, and suggests that ChatGPT is especially disadvantaged for LRLs
and African languages.

使用 FLORES-200 基准测试，我们提供了首个针对 204 种语言的实验证据和机器翻译成本分析，发现 GPT 模型在某些高资源语言上接近或超过传统机器翻译模型的性能，但在低资源语言上表现一直落后于传统机器翻译，对于我们覆盖的语言中的 84.1％，ChatGPT 的翻译能力低于传统机器翻译模型水平。我们的分析表明，语言的资源水平是决定 ChatGPT 相对翻译能力的最重要特征，并且暗示 ChatGPT 在低资源语言和非洲语言上处于劣势。