@article{alakeel-etal-2026-morphemes,
    title = "Morphemes without Borders: Evaluating Root{--}Pattern Morphology in {A}rabic Tokenizers and {LLM}s",
    author = "Alakeel, Yara Yousif  and
      Qwaider, Chatrine  and
      Aldarmaki, Hanan  and
      Alqahtani, Sawsan",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.923/",
    pages = "11787--11799",
    abstract = "This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root{--}pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed for analyzing how LLMs handle complex, non-concatenative forms and how tokenization choices influence this process. Our study begins with an evaluation of morphological fidelity across Arabic and multilingual tokenizers against gold-standard segmentation, followed by an analysis of LLM performance in productive root{--}pattern generation using a newly developed benchmark. Our findings across seven Arabic-centric and multilingual LLMs and their respective tokenizers reveal that tokenizer morphological alignment is not necessary nor sufficient for morphological generation, which questions the role of morphological tokenization in downstream performance."
}