Multilingual European Language Models: Benchmarking Approaches and Challenges
It addresses the lack of non-English benchmarks for evaluating multilingual LLMs, which is an incremental step in improving assessment methods.
This paper analyzed seven multilingual European benchmarks for large language models, identifying four major challenges and discussing solutions like human-in-the-loop verification to improve translation quality and reduce cultural biases.
The breakthrough of generative large language models (LLMs) that can solve different tasks through chat interaction has led to a significant increase in the use of general benchmarks to assess the quality or performance of these models beyond individual applications. There is also a need for better methods to evaluate and also to compare models due to the ever increasing number of new models published. However, most of the established benchmarks revolve around the English language. This paper analyses the benefits and limitations of current evaluation datasets, focusing on multilingual European benchmarks. We analyse seven multilingual benchmarks and identify four major challenges. Furthermore, we discuss potential solutions to enhance translation quality and mitigate cultural biases, including human-in-the-loop verification and iterative translation ranking. Our analysis highlights the need for culturally aware and rigorously validated benchmarks to assess the reasoning and question-answering capabilities of multilingual LLMs accurately.