{"total":67,"rows":[{"id":"2502.00894","title":"MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies","created":"2025-02-02","cited_by_count":25,"area":null},{"id":"2509.02550","title":"PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture","created":"2025-09-02","cited_by_count":21,"area":null},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2505.18152","title":"Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs","created":"2025-05-23","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":"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":"2508.08287","title":"Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2509.01081","title":"Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation","created":"2025-09-01","cited_by_count":10,"area":"lr"},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2601.07528","title":"From RAG to Agentic RAG for Faithful Islamic Question Answering","created":"2026-01-12","cited_by_count":9,"area":"agents"},{"id":"2503.17485","title":"SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia","created":"2025-03-21","cited_by_count":8,"area":null},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2603.23750","title":"IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge","created":"2026-03-24","cited_by_count":7,"area":null},{"id":"2503.15003","title":"LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?","created":"2025-03-19","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":"2510.27543","title":"DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models","created":"2025-10-31","cited_by_count":6,"area":null},{"id":"2505.09595","title":"WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models","created":"2025-05-14","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":"2508.08139","title":"Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models","created":"2025-08-11","cited_by_count":5,"area":"agents"},{"id":"2509.14008","title":"Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2602.21226","title":"IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2505.17021","title":"ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2508.15854","title":"QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning","created":"2025-08-20","cited_by_count":4,"area":"lr"},{"id":"2508.11260","title":"UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs?","created":"2025-08-15","cited_by_count":3,"area":"lr"},{"id":"2510.24328","title":"Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2512.24235","title":"LAILA: A Large Trait-Based Dataset for Arabic Automated Essay Scoring","created":"2025-12-30","cited_by_count":3,"area":null},{"id":"2602.01714","title":"MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.07036","title":"MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.08501","title":"Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA","created":"2026-03-09","cited_by_count":3,"area":"agents"},{"id":"2505.19766","title":"PAM: Training Policy-Aligned Moderation Filters at Scale","created":"2025-05-26","cited_by_count":2,"area":"safety"},{"id":"2506.11602","title":"Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2508.17324","title":"CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2509.18792","title":"Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing","created":"2025-09-23","cited_by_count":2,"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":"2604.19098","title":"SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.17007","title":"HalluScore: Large Language Model Hallucination Question Answering Benchmark","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2607.20219","title":"HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2504.11814","title":"ARWI: Arabic Write and Improve","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2505.17082","title":"GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2508.12227","title":"Arabic Multimodal Machine Learning: Datasets, Applications, Approaches, and Challenges","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2508.15796","title":"Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.14689","title":"HARNESS: Lightweight Distilled Arabic Speech Foundation Models","created":"2025-09-18","cited_by_count":1,"area":"distill"},{"id":"2510.24438","title":"Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content","created":"2025-10-28","cited_by_count":1,"area":"agents"},{"id":"2603.15773","title":"Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.23972","title":"Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith","created":"2026-03-25","cited_by_count":1,"area":"rag"},{"id":"2604.16396","title":"QU-NLP at QIAS 2026: Multi-Stage QLoRA Fine-Tuning for Arabic Islamic Inheritance Reasoning","created":"2026-03-29","cited_by_count":1,"area":"lr"},{"id":"2604.27766","title":"Instruction-Guided Poetry Generation in Arabic and Its Dialects","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.16364","title":"WASIL: In-the-Wild Arabic Spoken Interactions with LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.05531","title":"Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2608.03966","title":"HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2508.15797","title":"Benchmarking the Medical Understanding and Reasoning of Large Language Models in Arabic Healthcare Tasks","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2510.13481","title":"Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.16783","title":"LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2511.18411","title":"SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2603.01009","title":"Qayyem: A Real-time Platform for Scoring Proficiency of Arabic Essays","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2604.03380","title":"Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.06456","title":"Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.14186","title":"HARNESS: Lightweight Distilled Arabic Speech Foundation Models","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.09875","title":"Integrating Local and Global Entropy for Uncertainty Quantification in LLMs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16629","title":"Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.03936","title":"Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.09698","title":"VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.21985","title":"Redteaming Leading Arabic LLMs with ASAS","created":"2026-08-22","cited_by_count":0,"area":"safety"},{"id":"2608.29378","title":"Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration","created":"2026-08-29","cited_by_count":0,"area":"alignment"},{"id":"2609.16006","title":"Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.38355","title":"Halluscoring 2026: The first shared task on llms hallucination detection and answer verification","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}