@inproceedings{ibrahim-etal-2026-bigger,
    title = "When Bigger Isn{'}t Better: Evaluating {LLM}s for {A}rabic Sentiment Analysis",
    author = "Ibrahim, Mohamed  and
      Makki, Abdullah  and
      Barakat, Youssef  and
      Samy, Nour  and
      AlHumoud, Sarah",
    editor = "Al-Khalifa, Hend  and
      El-Haj, Mo  and
      Ezzini, Saad",
    booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.osact-1.4/",
    doi = "10.63317/2kimof4u6y8x",
    pages = "35--39",
    abstract = "This study evaluates the performance of a fine-tuned Arabic sentiment transformer (CAMeL-MSA) against eight large language models (LLMs). Using zero-shot prompting across six Arabic sentiment datasets, we compare a specialized, task-specific approach against generalized model capabilities. Results show that the fine-tuned baseline substantially outperformed all LLMs on five of the six datasets in both accuracy and Macro F1-score. While LLMs offer versatility, this comparison highlights the continued practical superiority of task-specific fine-tuning over zero-shot prompting."
}