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

arXiv:2610.11510 · cs.CL · Submitted 2026-10-08 · Read on arXiv

cs.CL

Submitted: 2026-10-08

Updated: 2026-10-08

Comments: EMNLP 2026

Code: https://github.com/abduABS/MSA_Dominance_LLM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 8× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Linear probe — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Transformer — 4× in this paper · explained in 2 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Cross-lingual Transfer — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Does Modern Standard Arabic — 2× in this paper
• Entanglement — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Parallel Universal Dependencies — 2× in this paper
• Empirical Coverage — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
• When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models
• The Llama 3 Herd of Models
• ArabianGPT: Native Arabic GPT-based Large Language Model
• Lost in Translation: Large Language Models in Non-English Content Analysis
• Qwen2.5 Technical Report
• Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering