@inproceedings{rabih-etal-2026-llms,
    title = "Can {LLM}s Control Readability? A Multi-Dimensional Evaluation Framework for {CEFR}-Controlled {A}rabic Generation",
    author = "Rabih, Nour  and
      Qwaider, Chatrine  and
      Briscoe, Ted",
    editor = "Shardlow, Matthew  and
      Fran{\c{c}}ois, Thomas  and
      Amaro, Raquel  and
      Baptista, Jorge  and
      Cardon, R{\'e}mi  and
      Ribeiro, Eug{\'e}nio  and
      Saggion, Horacio  and
      Stodden, Regina  and
      Todirascu, Amalia  and
      Wilkens, Rodrigo",
    booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/test-year-match/2026.readi-1.6/",
    doi = "10.63317/48v7mxywgfja",
    pages = "74--88",
    abstract = "While Large Language Models (LLMs) can generate fluent Arabic text, their ability to reliably control readability levels remains unclear. We propose a multi-dimensional evaluation framework for Common European Framework of Reference for Language (CEFR)-controlled Arabic text generation, assessing whether instruction-following LLMs can serve as reliable generators for adaptive language learning. Our framework integrates controlled prompting, automatic readability prediction using a validated Taha-19 model, lexical constraint validation, and syntactic complexity profiling. Results show that structured prompting substantially improves CEFR alignment. In particular, CEFR-guided prompting with lexical constraints achieves the highest conformity to reference linguistic profiles (0.91 cosine similarity) and near-perfect agreement with predicted readability levels (0.99), while unconstrained prompting exhibits weak control. These findings establish an empirical foundation for integrating readability-aware Arabic text generation into adaptive educational systems."
}