{"total":13,"rows":[{"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":"2508.16357","title":"MizanQA: Benchmarking Large Language Models on Moroccan Legal Question Answering","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2509.22589","title":"ArabJobs: A Multinational Corpus of Arabic Job Ads","created":"2025-09-26","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":"2508.20047","title":"AraHealthQA 2025: The First Shared Task on Arabic Health Question Answering","created":"2025-08-27","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":"2602.05374","title":"Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.05692","title":"MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2505.18331","title":"PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2509.11365","title":"!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2604.03395","title":"Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation","created":"2026-04-03","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":"2608.00207","title":"Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}