A Benchmark to Evaluate LLMs' Proficiency on Italian Student Competencies

Abstract

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to generate and manipulate human language, highlighting their potential across various applications. Evaluating LLMs in languages other than English is crucial for ensuring their linguistic versatility, cultural relevance, and applicability in diverse global contexts, thus broadening their usability and effectiveness. We tackle this challenge by introducing a structured benchmark using the INVALSI tests, a set of well-established assessments designed to measure educational competencies across Italy. Our study makes three primary contributions: First, we adapt the INVALSI tests as a benchmark for automated LLM evaluation, rigorously adapting the test format to suit automated processing while retaining the essence of the original tests. Second, we provide a detailed assessment of current LLMs, offering a crucial reference point for the academic community. Finally, we visually compare the performance of these models against human results. Additionally, our benchmark is publicly available and provided with a comprehensive evaluation suite ( https://github.com/Crisp-Unimib/INVALSI-Eval-Suite ), ensuring that the benchmark remains a current and valuable resource relevant for advancing industrial-strength NLP applications.