UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment

TL;DR

UniversalCEFR is a comprehensive multilingual dataset of texts annotated with CEFR levels, facilitating open research and benchmarking in automated language proficiency assessment across 13 languages.

Contribution

It introduces a standardized, large-scale multilingual dataset and evaluates multiple modeling approaches for CEFR level classification.

Findings

Linguistic features and fine-tuned models perform well in CEFR assessment.

UniversalCEFR enables consistent cross-lingual proficiency research.

Benchmarking results guide future model development.

Abstract

We introduce UniversalCEFR, a large-scale multilingual and multidimensional dataset of texts annotated with CEFR (Common European Framework of Reference) levels in 13 languages. To enable open research in automated readability and language proficiency assessment, UniversalCEFR comprises 505,807 CEFR-labeled texts curated from educational and learner-oriented resources, standardized into a unified data format to support consistent processing, analysis, and modelling across tasks and languages. To demonstrate its utility, we conduct benchmarking experiments using three modelling paradigms: a) linguistic feature-based classification, b) fine-tuning pre-trained LLMs, and c) descriptor-based prompting of instruction-tuned LLMs. Our results support using linguistic features and fine-tuning pretrained models in multilingual CEFR level assessment. Overall, UniversalCEFR aims to establish best practices in data distribution for language proficiency research by standardising dataset formats, and promoting their accessibility to the global research community.