Classifying German Language Proficiency Levels Using Large Language Models

TL;DR

This study explores the application of Large Language Models to automatically classify German texts into CEFR proficiency levels, demonstrating improved accuracy and scalability over previous methods.

Contribution

It introduces a diverse dataset combining real and synthetic data and evaluates multiple LLM-based approaches for CEFR classification, showing their effectiveness.

Findings

Prompt-engineering enhances classification accuracy.

Fine-tuning LLaMA-3-8B-Instruct improves performance.

Probing internal neural states offers reliable classification.

Abstract

Assessing language proficiency is essential for education, as it enables instruction tailored to learners needs. This paper investigates the use of Large Language Models (LLMs) for automatically classifying German texts according to the Common European Framework of Reference for Languages (CEFR) into different proficiency levels. To support robust training and evaluation, we construct a diverse dataset by combining multiple existing CEFR-annotated corpora with synthetic data. We then evaluate prompt-engineering strategies, fine-tuning of a LLaMA-3-8B-Instruct model and a probing-based approach that utilizes the internal neural state of the LLM for classification. Our results show a consistent performance improvement over prior methods, highlighting the potential of LLMs for reliable and scalable CEFR classification.