{"total":18,"rows":[{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46,"area":null},{"id":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30,"area":null},{"id":"2402.17478","title":"Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles","created":"2024-02-27","cited_by_count":21,"area":null},{"id":"2308.10783","title":"Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis","created":"2023-08-21","cited_by_count":20,"area":null},{"id":"2311.09812","title":"Large Language Models for Propaganda Span Annotation","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2407.12797","title":"CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2408.07983","title":"ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2409.07054","title":"Native vs Non-Native Language Prompting: A Comparative Analysis","created":"2024-09-11","cited_by_count":9,"area":null},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2410.15308","title":"LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2406.03916","title":"ArMeme: Propagandistic Content in Arabic Memes","created":"2024-06-06","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":"2407.07321","title":"Benchmarking LLMs for Environmental Review and Permitting","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2406.05559","title":"ThatiAR: Subjectivity Detection in Arabic News Sentences","created":"2024-06-08","cited_by_count":2,"area":null},{"id":"2311.03184","title":"Nexus at ArAIEval Shared Task: Fine-Tuning Arabic Language Models for Propaganda and Disinformation Detection","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2604.27637","title":"Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2603.18173","title":"GRAFITE: Generative Regression Analysis Framework for Issue Tracking and Evaluation","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}