{"total":31,"rows":[{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129,"area":null},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123,"area":null},{"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":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"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":"2308.04945","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","created":"2023-08-09","cited_by_count":20,"area":null},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"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":"2404.02403","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","created":"2024-04-03","cited_by_count":11,"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":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"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":"2509.20045","title":"Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks","created":"2025-09-24","cited_by_count":9,"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":"2407.04459","title":"Generalists vs. Specialists: Evaluating Large Language Models for Urdu","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2501.13419","title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2406.05559","title":"ThatiAR: Subjectivity Detection in Arabic News Sentences","created":"2024-06-08","cited_by_count":2,"area":null},{"id":"2506.03458","title":"Culture Matters in Toxic Language Detection in Persian","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2309.12863","title":"Domain Adaptation for Arabic Machine Translation: The Case of Financial Texts","created":"2023-09-22","cited_by_count":1,"area":null},{"id":"2410.11006","title":"Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs","created":"2024-10-14","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":"2312.15304","title":"Exploring the Capabilities of ChatGPT in Ancient Chinese Translation and Person Name Recognition","created":"2023-12-23","cited_by_count":0,"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":"2405.00704","title":"A Survey on the Real Power of ChatGPT","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2411.00045","title":"A Novel Psychometrics-Based Approach to Developing Professional Competency Benchmark for Large Language Models","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2505.04640","title":"A Comparative Benchmark of a Moroccan Darija Toxicity Detection Model (Typica.ai) and Major LLM-Based Moderation APIs (OpenAI, Mistral, Anthropic)","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2509.13775","title":"Exploring Data and Parameter Efficient Strategies for Arabic Dialect Identifications","created":"2025-09-17","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":"2607.25814","title":"Evaluation of Adversarial Robustness in Arabic Language Models","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}