Work

Are Dialects Better Prompters? A Case Study on Arabic Subjective Text Classification

Year: 2025

Type: conference-paper

Abstract: This paper investigates the effect of dialectal prompting, variations in prompting script and model fine-tuning on subjective classification in Arabic dialects.To this end, we evaluate the performances of 12 widely used open source LLMs across four tasks and eight benchmark datasets.Our results reveal that specialized fine-tuned models with Arabic and Arabizi scripts dialectal prompts achieve the best results, which provides new findings on the finetuning of LLMs for low-resource languages.

DOI: 10.18653/v1/2025.findings-acl.892

Authors: Leila Moudjari, Farah Benamara

Institutions: Institut de Recherche en Informatique de Toulouse, Université de Toulouse, Agency for Science, Technology and Research, Centre National de la Recherche Scientifique, National University of Singapore, Image and Pervasive Access Laboratory

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W4412888074

FWCI: 1.059

Cites:

Cited by: 1

Related to: 10