This study presents a novel approach to assessing French text readability for adults with low literacy skills, addressing both global (full-text) and local (segment-level) difficulty. We introduce a dataset of 461 texts annotated using a difficulty scale developed specifically for this population. Using this corpus, we conducted a systematic comparison of key readability modeling approaches, including machine learning techniques based on linguistic variables, fine-tuning of CamemBERT, a hybrid approach combining CamemBERT with linguistic variables, and the use of generative language models (LLMs) to carry out readability assessment at both global and local levels.

We present the iRead4Skills Intelligent Complexity Analyzer, an open-access platform specifically designed to assist educators and content developers in addressing the needs of low-literacy adults by analyzing and diagnosing text complexity. This multilingual system integrates a range of Natural Language Processing (NLP) components to assess input texts along multiple levels of granularity and linguistic dimensions in Portuguese, Spanish, and French. It assigns four tailored difficulty levels using state-of-the-art models, and introduces four diagnostic yardsticks—textual structure, lexicon, syntax, and semantics—offering users actionable feedback on specific dimensions of textual complexity. Each component of the system is supported by experiments comparing alternative models on manually annotated data.

Nous présentons une nouvelle formule de lisibilité en français spécifiquement conçue pour les personnes en situation d’illettrisme. À cette fin, nous avons construit un corpus de 461 textes annotés selon une échelle de difficulté spécialisée à ce public. Dans un second temps, nous avons systématiquement comparé les principales approches en lisibilité, incluant l’apprentissage automatique reposant sur des variables linguistiques, le fine-tuning de CamemBERT, une approche hybride combinant CamemBERT et des variables linguistiques et des modèles de langue génératifs (LLMs). Une analyse approfondie de ces modèles et de leurs performances est menée afin d’évaluer leur applicabilité dans des contextes réels.