Testing Low-Resource Language Support in LLMs Using Language Proficiency Exams: the Case of Luxembourgish
This addresses the lack of evaluation tools for low-resource languages like Luxembourgish, though it is incremental as it applies existing methods to a new context.
The study tackled the problem of evaluating LLMs for low-resource languages by using language proficiency exams for Luxembourgish, finding that large models like Claude and DeepSeek-R1 achieve high scores while smaller models perform poorly, and that these exam scores can predict performance in other NLP tasks.
Large Language Models (LLMs) have become an increasingly important tool in research and society at large. While LLMs are regularly used all over the world by experts and lay-people alike, they are predominantly developed with English-speaking users in mind, performing well in English and other wide-spread languages while less-resourced languages such as Luxembourgish are seen as a lower priority. This lack of attention is also reflected in the sparsity of available evaluation tools and datasets. In this study, we investigate the viability of language proficiency exams as such evaluation tools for the Luxembourgish language. We find that large models such as Claude and DeepSeek-R1 typically achieve high scores, while smaller models show weak performances. We also find that the performances in such language exams can be used to predict performances in other NLP tasks in Luxembourgish.