Arabic Language Models

Latest papers

26 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining
Oct 21, 2026Houssam Eddine Boukhalfa, Mourad Bouache, Mourad DahmaneArabic Language Models Language Model Pretraining
National School of Artificial Intelligence (ENSIA), Algiers, Algeria · Nojoom AI
Aligning Cultural Behaviors in Arabic Language Models via Preferences
Oct 18, 2026Junhong Liang, Daniil Orel, Saeed Almheiri +11Arabic Language Models Cultural Alignment
Mohamed bin Zayed University of Artificial Intelligence · IBM Research AI
Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis
Oct 8, 2026Abdu Sallouh, Nicholas Popovič, Michael FärberArabic Language Models Arabic NLP
Technical University of Dresden · Mohamed bin Zayed University of Artificial Intelligence · ScaDS.AI, TU Dresden
AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic
Sep 28, 2026Ignacio Iacobacci, Faroq Altam, Zhaozhi Qian +1LLM Evaluation Arabic NLP
Elm Company
Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
Sep 25, 2026Yahya Mohamed ElnawasanyConversational Agents Arabic Language Models
Independent Researcher, Egypt
A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model
Sep 22, 2026Imad Lakim, Ebtesam Almazrouei, Ibrahim Abu Alhaol +2Arabic Language Models Energy-Efficient ML
TII, Abu Dhabi · LightOn, Paris
Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs
Sep 21, 2026Mai Mohamed Eida, Ryan Dolan, Paul de Nijs +1Dialect Bias in Language Models Language Model Bias Evaluation
University of Illinois Urbana Champaign
Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
Sep 10, 2026Yingzhi Wang, Reem Alhazzani, Muhammad AlqurishiAudio-Language Model Evaluation Audio QA
Elm Company, KSA
YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models
Sep 9, 2026Mahmoud Reda, Salam Khalifa, Reham Marzouk +1Multilingual Language Model Evaluation Arabic NLP
New York University Abu Dhabi · Stony Brook University · Mohamed bin Zayed University of Artificial Intelligence
Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models
Aug 30, 2026Ghassan Al-Sumaidaee, Sajjad Abdoli, Ahmed Rashad +1Multilingual Language Model Evaluation LLM Evaluation
1Perle
Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration
Aug 29, 2026Mohamad Zbib, Ammar MohannaArabic Language Models Refusal Behavior in Language Models
American University of Beirut
Extractive Summarization for Arabic Documents Using SAraBERT with a Semantic Siamese Similarity Evaluation Metric
Aug 21, 2026Sami Shames El Deen, Mariette AwadArabic Language Models Text Summarization
American University of Beirut
AraSSM: A bidirectional state-space encoder for Arabic masked language modeling
Aug 8, 2026Ahmed Amine Aliane, Hassina Aliane, Nasredine SemmarLanguage Model Pretraining Arabic NLP
Arabic Institute for Translation, Algiers, Algeria · CERIST, Algeria · CEA LIST, Paris-Saclay, France
ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification
Aug 2, 2026Wajdi Zaghouani, Md. Rafiul Biswas, Kholoud Khalil Aldous +1LLM Safety Benchmarks Arabic NLP
Northwestern University in Qatar, Qatar · Hamad Bin Khalifa University, Qatar
Does Machine "know" interpersonal pragmatics? Evidence from MARBERT's learning of emoji pragmatics in Arabic digital discourse
Aug 2, 2026Mohammed Q. ShormaniArabic NLP Arabic Language Models
Ibb University · Ibb University, Ibb, Yemen
CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations
Jul 17, 2026Suzan Awinat, Alfonso Ortega del PuenteRepresentation Geometry in Language Models Arabic NLP
Department of Computer Engineering Autonomous University of Madrid (UAM) School of Science and Technology IE University Madrid, Spain · Department of Computer Science Oviedo University Asturias, Spain
Evaluation of Small Language Models for Arabic Language Processing
Jun 19, 2026Jumana Alsubhi, Ahmed Alhusayni, Abdulrahman Gharawi +5Arabic NLP Small Language Models
Naseej Innovation Lab, Naseej for Technology, Riyadh, Saudi Arabia.
RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment
Apr 10, 2026Jaber Jaber, Osama JaberLanguage Model Vocabulary Expansion Arabic Language Models
RightNow AI
State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation
Apr 7, 2026Navan Preet Singh, Anurag Garikipati, Ahmed Abulkhair +6Arabic Language Models Arabic NLP
Forta, Houston, TX · Incept Labs, Houston, TX · Titan Holdings, San Francisco, CA
Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation
Apr 3, 2026Leen AlQadi, Ahmed Alzubaidi, Mohammed Alyafeai +6LLM Evaluation Benchmark Validity
Technology Innovation Institute, Abu Dhabi, UAE
Fanar 2.0: Arabic Generative AI Stack
Mar 17, 2026FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad +34Arabic Language Models Arabic NLP
Qatar Computing Research Institute (QCRI), Hamad Bin Khalifa University
Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs
Mar 16, 2026Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki +1Arabic NLP Arabic Language Models
Saudi Data & AI Authority (SDAIA) · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Princess Nourah Bint Abdulrahman University (PNU)
From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning
Mar 4, 2026Omer Nacar, Deema Alquffari, Saleh Alsharideh +22Arabic Language Models LLM Fine-Tuning
Tuwaiq Academy, Riyadh, Saudi Arabia · Wakeb Company · Tahakom +3
ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning
Feb 19, 2026Hussein S. Al-Olimat, Ahmad AlshareefArabic NLP Arabic Language Models
Independent Researchers
Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generation
Feb 18, 2026Jonathan Mutal, Perla Al Almaoui, Simon Hengchen +1Arabic NLP Arabic Dialects
Faculté de traduction et d’interprétation, Université de Genève
SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models
Feb 3, 2026Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh +2LLM Safety Benchmarks Multilingual Language Model Evaluation
Compumacy for Artificial Intelligence Solutions, Cairo, Egypt · Computer Science Department, College of Computer Science and Engineering, Taibah University, Yanbu 46522, KSA · Electrical and Computer Engineering Department, George Mason University, VA, USA +2

Oct 21, 2026J/K move · Enter open · S save

AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining

Houssam Eddine Boukhalfa, Mourad Bouache, Mourad Dahmane

National School of Artificial Intelligence (ENSIA), Algiers, Algeria · Nojoom AI

Arabic Language Models Language Model Pretraining Arabic NLP Efficient Language Model Training Domain Adaptation for LLMs Training Data Curation

Open paper AskPDF arXiv

Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality Language), a time- and resource-efficient framework for adapting a multilingual LLM to Modern Standard Arabic (MSA). AQL-Lite couples a quality-first curation pipeline (structural cleaning, heuristic and model-based filtering, MSA selection, and deduplication) with a partial-parameter CPT recipe that trains RS-LoRA adapters across the network together with the last eight transformer blocks and the embedding matrix, under layer-wise learning rates. At a matched 1B-token budget, CPT on AQL-curated data raises a four-benchmark Arabic mean by 3.51 points over CPT on raw web text, which yields no gain over the base model. In a controlled 5B-token comparison, AQL-Lite recovers 94% of the gain of full-parameter CPT (mean 73.19 vs. 73.58) in 52% of the wall-clock time and outperforms adapter-only baselines on every benchmark, and a component ablation shows that adapters, unfrozen blocks, and embedding training each contribute. Scaled to 40B MSA tokens and instruction-tuned on one million examples, the resulting 12B model scores 75.3 on the seven-benchmark Open Arabic LLM Leaderboard v2 (OALL v2) suite. These results suggest that partial-parameter CPT on a carefully curated corpus is a practical route to efficient MSA adaptation.