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.

This paper presents the system developed by the NGU_CNLP team for addressing the shared task on Propaganda Detection in Arabic at WANLP 2022. The team participated in the shared tasks’ two sub-tasks which are: 1) Propaganda technique identification in text and 2) Propaganda technique span identification. In the first sub-task, the goal is to detect all employed propaganda techniques in some given piece of text out of a possible 17 different techniques or to detect that no propaganda technique is being used in that piece of text. As such, this first sub-task is a multi-label classification problem with a pool of 18 possible labels. Subtask 2 extends sub-task 1, by requiring the identification of the exact text span in which a propaganda technique was employed, making it a sequence labeling problem. For task 1, a combination of a data augmentation strategy coupled with an enabled transformer-based model comprised our classification model. This classification model ranked first amongst the 14 systems participating in this subtask. For sub-task two, a transfer learning model was adopted. The system ranked third among the 3 different models that participated in this subtask.