# Experiments with Universal CEFR Classification

arXiv: https://arxiv.org/abs/1804.06636 · HTML: https://mlsanity.com/paper/1804.06636/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2018.

## Built on by (most cited first, 17 of 17)

- [A Systematic Review of Reproducibility Research in Natural Language Processing](https://mlsanity.com/paper/2103.07929/) (2021)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Automatic Readability Assessment for Closely Related Languages](https://mlsanity.com/paper/2305.13478/) (2023)
- [Quantified Reproducibility Assessment of NLP Results](https://mlsanity.com/paper/2204.05961/) (2022)
- [Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation](https://mlsanity.com/paper/2402.12593/) (2024)
- [Are pre-trained text representations useful for multilingual and multi-dimensional language proficiency modeling?](https://mlsanity.com/paper/2102.12971/) (2021)
- [Text mining in education](https://mlsanity.com/paper/2403.00769/) (2024)
- [EXPATS: A Toolkit for Explainable Automated Text Scoring](https://mlsanity.com/paper/2104.03364/) (2021)
- [BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages](https://mlsanity.com/paper/2310.11584/) (2023)
- [GrammarTagger: A Multilingual, Minimally-Supervised Grammar Profiler for Language Education](https://mlsanity.com/paper/2104.03190/) (2021)
- [Semi-Supervised Joint Estimation of Word and Document Readability](https://mlsanity.com/paper/2104.13103/) (2021)
- [Quantifying Reproducibility in NLP and ML](https://mlsanity.com/paper/2109.01211/) (2021)
- [QRA++: Quantified Reproducibility Assessment for Common Types of Results in Natural Language Processing](https://mlsanity.com/paper/2505.17043/) (2025)
- [Classifying German Language Proficiency Levels Using Large Language Models](https://mlsanity.com/paper/2512.06483/) (2025)
- [Project MOSLA: Recording Every Moment of Second Language Acquisition](https://mlsanity.com/paper/2403.17314/) (2024)
- [Towards interpretable models for language proficiency assessment: Predicting the CEFR level of Estonian learner texts](https://mlsanity.com/paper/2602.13102/) (2026)
- [Multilingual Embedding Probes Fail to Generalize Across Learner Corpora](https://mlsanity.com/paper/2604.07095/) (2026)

## Abstract (arXiv)

The Common European Framework of Reference (CEFR) guidelines describe language proficiency of learners on a scale of 6 levels. While the description of CEFR guidelines is generic across languages, the development of automated proficiency classification systems for different languages follow different approaches. In this paper, we explore universal CEFR classification using domain-specific and domain-agnostic, theory-guided as well as data-driven features. We report the results of our preliminary experiments in monolingual, cross-lingual, and multilingual classification with three languages: German, Czech, and Italian. Our results show that both monolingual and multilingual models achieve similar performance, and cross-lingual classification yields lower, but comparable results to monolingual classification.