{"total":44,"rows":[{"id":"2103.06678","title":"The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models","created":"2021-03-11","cited_by_count":119,"area":null},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"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":"2102.10684","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","created":"2021-02-21","cited_by_count":39,"area":null},{"id":"2106.13000","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","created":"2021-06-24","cited_by_count":38,"area":null},{"id":"2305.14976","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2310.16117","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","created":"2023-10-24","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"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":"2310.13747","title":"ALDi: Quantifying the Arabic Level of Dialectness of Text","created":"2023-10-20","cited_by_count":24,"area":null},{"id":"2210.09582","title":"NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task","created":"2022-10-18","cited_by_count":23,"area":null},{"id":"2407.04910","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","created":"2024-07-06","cited_by_count":23,"area":null},{"id":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2201.06723","title":"Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech","created":"2022-01-18","cited_by_count":14,"area":null},{"id":"2310.13661","title":"Arabic Dialect Identification under Scrutiny: Limitations of Single-label Classification","created":"2023-10-20","cited_by_count":13,"area":null},{"id":"2409.17912","title":"Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2407.03020","title":"Exploiting Dialect Identification in Automatic Dialectal Text Normalization","created":"2024-07-03","cited_by_count":7,"area":null},{"id":"2509.02038","title":"NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task","created":"2025-09-02","cited_by_count":7,"area":null},{"id":"2209.07611","title":"Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties","created":"2022-09-15","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":"2103.01065","title":"Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task","created":"2021-03-01","cited_by_count":5,"area":null},{"id":"2105.04221","title":"Similarities between Arabic Dialects: Investigating Geographical Proximity","created":"2021-05-10","cited_by_count":5,"area":null},{"id":"2106.06017","title":"Cross-lingual Emotion Detection","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2403.11130","title":"Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models","created":"2024-03-17","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":"2201.06496","title":"ArCovidVac: Analyzing Arabic Tweets About COVID-19 Vaccination","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2307.07436","title":"Towards spoken dialect identification of Irish","created":"2023-07-14","cited_by_count":3,"area":null},{"id":"2203.00271","title":"ArabGend: Gender Analysis and Inference on Arabic Twitter","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2205.07960","title":"Meta AI at Arabic Hate Speech 2022: MultiTask Learning with Self-Correction for Hate Speech Classification","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2210.12314","title":"A Benchmark Study of Contrastive Learning for Arabic Social Meaning","created":"2022-10-22","cited_by_count":2,"area":null},{"id":"2505.21816","title":"Revisiting Common Assumptions about Arabic Dialects in NLP","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2603.16601","title":"Tarab: A Multi-Dialect Corpus of Arabic Lyrics and Poetry","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2607.19751","title":"Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction","created":"2026-07-22","cited_by_count":1,"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":"2506.19753","title":"Arabic Dialect Classification using RNNs, Transformers, and Large Language Models: A Comparative Analysis","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2512.04257","title":"Computational Linguistics Meets Libyan Dialect: A Study on Dialect Identification","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.07941","title":"Moonworks Lunara Aesthetic Dataset","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.12937","title":"Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.08125","title":"Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2608.01291","title":"ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.14829","title":"Enemray: Toward Capable Language Models for Hassaniya","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}