Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs

Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis

Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic. A natural explanation is that their internal representations are dominated by MSA. We test this hypothesis by adapting the language-dominance framework of Shani and Basirat (2025)...

The Arabic Bible as an Evaluation Tool: The Case Study of the Khalīlī Arabic Dialect

Syllable Structure Variation between Two Iraqi Arabic Dialects: A Comparative Optimality-Theoretic Investigation

This study is an Optimality-Theoretic comparison of two major dialects of Iraqi Arabic: Baghdadi Gilit Arabic (BGD) and Basri Arabic (BAS), focusing on syllable structure variation. The data were collected from 20 native speakers (10 for each dialect), representing both rural and urban backgrounds, as participants in r...

Loanwords of Arabic Origin in Northern Talyshi through the Lens of Tolışon Sədo Newspaper

This study explores Arabic-origin loanwords in Northern Talyshi, addressing a significant gap in existing scholarship. Although the Talyshi language has been the subject of linguistic research for nearly two centuries, its lexicon – particularly borrowed vocabulary – remains largely understudied. Prior work has foc...

Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models

Large language models are increasingly deployed in Arabic-speaking markets, yet standard benchmarks overwhelmingly reward Modern Standard Arabic (MSA) fluency while leaving dialectal and culturally grounded competence unmeasured. This gap is consequential: everyday Arabic is largely dialectal, and dialect encodes socia...

EDRAC: Benchmarking Arabic Dialect Reading Comprehension

This work introduces EDRAC, the first large-scale benchmark for dialectal Arabic machine reading comprehension (MRC) and generative QA, covering five major dialects: Egyptian, Moroccan, Emirati, Syrian, and Saudi Arabic, and benchmarks Arabic-centric and multilingual LLMs on EDRAC using lexical and semantic metrics.