Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representation for the less prestigious Sa'idi Egyptian Arabic (SEA) dialect both in LLM and resource development. Does this lack of representation influence an LLM's view of the acceptability of SEA (upstream), and does an upstream bias against SEA lead to worse performance (downstream)? We investigate the upstream effect of SEA dialectal features on LLM preferences in a Targeted Syntactic Evaluation (TSE) task which reveals a significant bias against SEA across multiple LLMs. We then analyze the effect of these same features on downstream model performance on MMLU benchmarks and show that models experience a degradation in performance when presented with SEA. This work highlights the need for further exploration on how sub-dialectal variation impacts language technologies.
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)...
Abdu Sallouh, Nicholas Popovic, Michael Färber· 0 citations
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...
Israa Ali Kareem Al-Aaydi· مجلة واسط للعلوم الانسانية· 0 citations
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...
Hakob Avchyan· Journal of Language Contact· 0 citations
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...
Ghassan Al-Sumaidaee, Sajjad Abdoli, Ahmed Rashad et al.· 0 citations
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.
Noor Abo Mokh, K. Chirkunov, Teresa Lynn et al.· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comOct 22, 2026
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
