@article{hamed-etal-2026-benchmarking,
    title = "Benchmarking {A}rabic Authorship Attribution and Style Transfer with Large Language Models",
    author = "Hamed, Injy  and
      Alhafni, Bashar  and
      Habash, Nizar  and
      Solorio, Thamar",
    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.576/",
    pages = "7262--7278",
    abstract = "Writing style is a fundamental component of natural language. However, significant research gaps remain in two key style-centric tasks: authorship attribution (AA) and authorship style transfer, particularly for Arabic. In this work, we revisit both tasks in that context. We introduce a new AA dataset comprising texts in Modern Standard and Dialectal Arabic. We train transformer-based AA models using dual cross-entropy and contrastive learning loss objectives, and validate model performance through human evaluation. We then utilize the trained AA model to benchmark a range of large language models (LLMs) on style recognition and generation tasks, providing new insights into their capabilities in modeling Arabic writing styles. Our work reveals limitations of current models and provides resources to advance research in this direction."
}