Comparative Evaluation of Transformer-Based Models for Plain Language Classification in Hungarian Legal–Administrative Texts
Electronics · 06.07.2026 · 15 (13) · 2955
DOI: 10.3390/electronics15132955 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 06.07.2026. Verfasst von István Üveges. Die Arbeit nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Plain Language seeks to enhance the clarity and comprehensibility of legal and administrative communication; while Natural Language Processing (NLP) offers promising tools for assessing text complexity, most Plain Language classification studies focus exclusively on English, leaving low-resource languages underexplored. This study presents the first systematic evaluation of transformer-based models for sentence-level Plain Language classification in Hungarian tax administrative texts. We benchmarked zero-shot prompting with GPT-4o against fine-tuned open-weight and proprietary models, including huBERT, XLM-RoBERTa, GPT-4o-mini, and Gemini 1.0 Pro, and contextualized these results against previously established lightweight machine learning baselines based on term frequency-inverse document frequency with a support vector machine (TF-IDF + SVM) and fastText. To address data scarcity, we applied translation-based data augmentation using parallel Hungarian–English corpora. The best-performing model achieved a macro-average F1-score of 0.79. Mid-sized models also delivered competitive results, combining accuracy with feasible inference speed and deployment flexibility. Beyond classification performance, we conducted local and aggregated interpretability analysis based on Shapley-values to identify linguistic patterns influencing model decisions. This revealed alignment with known Plain Language features, such as nominalizations and syntactic complexity, as well as biases introduced by frequent domain-specific terms. Our findings demonstrate that Plain Language classifiers can be effectively adapted to low-resource legal–administrative domains. The results support the development of real-time feedback tools that promote linguistic accessibility and contribute to the broader goal of Access to Justice.
Zitieren
APA
Üveges, I. (2026). Comparative Evaluation of Transformer-Based Models for Plain Language Classification in Hungarian Legal–Administrative Texts. Electronics, 15(13), 2955. https://doi.org/10.3390/electronics15132955
Vancouver
Üveges I. Comparative Evaluation of Transformer-Based Models for Plain Language Classification in Hungarian Legal–Administrative Texts. Electronics. 2026;15(13):2955. doi:10.3390/electronics15132955
BibTeX
@article{veges2026,
author = {Üveges, István},
title = {Comparative Evaluation of Transformer-Based Models for Plain Language Classification in Hungarian Legal–Administrative Texts},
journal = {Electronics},
year = {2026},
volume = {15},
number = {13},
pages = {2955},
doi = {10.3390/electronics15132955}
}
EUVIMED