{"total":16,"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":"2603.23750","title":"IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge","created":"2026-03-24","cited_by_count":7,"area":null},{"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":"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":"2605.16364","title":"WASIL: In-the-Wild Arabic Spoken Interactions with LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2607.00139","title":"Benchmarking Frontier LLMs on Arabic Cultural and Sociolinguistic Knowledge: A Cross-Evaluation Framework with Human SME Ground Truth","created":"2026-06-30","cited_by_count":1,"area":null},{"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":"2601.19898","title":"DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.12768","title":"SectEval: Evaluating the Latent Sectarian Preferences of Large Language Models","created":"2026-03-13","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":"2606.16629","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":"2608.03720","title":"Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.18361","title":"Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.00999","title":"Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.20472","title":"ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}