{"total":44,"rows":[{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"area":null},{"id":"2305.14976","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2310.16117","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","created":"2023-10-24","cited_by_count":29,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2407.04910","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","created":"2024-07-06","cited_by_count":23,"area":null},{"id":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2410.17040","title":"Arabic Dataset for LLM Safeguard Evaluation","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2308.03051","title":"TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2403.09017","title":"AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic","created":"2024-03-14","cited_by_count":16,"area":null},{"id":"2503.00151","title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2505.18383","title":"NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2312.08400","title":"Beyond English: Evaluating LLMs for Arabic Grammatical Error Correction","created":"2023-12-13","cited_by_count":12,"area":null},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2506.01340","title":"The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technology","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2306.16322","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2510.13430","title":"Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps","created":"2025-10-15","cited_by_count":9,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2306.06800","title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2310.17333","title":"Arabic Fine-Grained Entity Recognition","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2405.06239","title":"SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora","created":"2024-05-10","cited_by_count":7,"area":null},{"id":"2410.04269","title":"RoQLlama: A Lightweight Romanian Adapted Language Model","created":"2024-10-05","cited_by_count":7,"area":null},{"id":"2509.02038","title":"NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task","created":"2025-09-02","cited_by_count":7,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2310.10260","title":"Prediction of Arabic Legal Rulings using Large Language Models","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2506.01920","title":"From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2308.04492","title":"ChatGPT for Arabic Grammatical Error Correction","created":"2023-08-08","cited_by_count":5,"area":null},{"id":"2408.03524","title":"EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora","created":"2024-08-07","cited_by_count":5,"area":null},{"id":"2412.04726","title":"BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English","created":"2024-12-06","cited_by_count":5,"area":null},{"id":"2507.15850","title":"3LM: Bridging Arabic, STEM, and Code through Benchmarking","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2507.22603","title":"BALSAM: A Platform for Benchmarking Arabic Large Language Models","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2511.14295","title":"AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2408.11219","title":"CoDi: Conversational Distillation for Grounded Question Answering","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2602.17054","title":"ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2401.07760","title":"On the importance of Data Scale in Pretraining Arabic Language Models","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2510.03502","title":"ALHD: A Large-Scale and Multigenre Benchmark Dataset for Arabic LLM-Generated Text Detection","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2606.21460","title":"Evaluation of Small Language Models for Arabic Language Processing","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2610.12742","title":"U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}