{"total":34,"rows":[{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"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":"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":"2102.10684","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","created":"2021-02-21","cited_by_count":39,"area":null},{"id":"2205.09651","title":"Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT","created":"2022-05-19","cited_by_count":33,"area":null},{"id":"2105.01279","title":"ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2109.06798","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","created":"2021-09-14","cited_by_count":16,"area":null},{"id":"2106.07540","title":"Evaluating Various Tokenizers for Arabic Text Classification","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2212.10755","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","created":"2022-12-21","cited_by_count":11,"area":null},{"id":"2411.01192","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","created":"2024-11-02","cited_by_count":10,"area":null},{"id":"2307.15045","title":"A Transformer-based Approach for Arabic Offline Handwritten Text Recognition","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2305.11244","title":"A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model","created":"2023-05-18","cited_by_count":8,"area":null},{"id":"2310.19034","title":"ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic","created":"2023-10-29","cited_by_count":8,"area":null},{"id":"2403.12392","title":"AraPoemBERT: A Pretrained Language Model for Arabic Poetry Analysis","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2305.12084","title":"Revisiting Entropy Rate Constancy in Text","created":"2023-05-20","cited_by_count":7,"area":null},{"id":"2306.06800","title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2405.06239","title":"SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora","created":"2024-05-10","cited_by_count":7,"area":null},{"id":"2103.09602","title":"On the Role of Images for Analyzing Claims in Social Media","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2310.16127","title":"Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2408.03524","title":"EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora","created":"2024-08-07","cited_by_count":5,"area":null},{"id":"2104.12201","title":"Transformers to Fight the COVID-19 Infodemic","created":"2021-04-25","cited_by_count":4,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null},{"id":"2601.02875","title":"Revisiting Data Compression with Language Modeling","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2210.09990","title":"Post-hoc analysis of Arabic transformer models","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2307.06218","title":"Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2502.05312","title":"Towards the Development of Balanced Synthetic Data for Correcting Grammatical Errors in Arabic: An Approach Based on Error Tagging Model and Synthetic Data Generating Model","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2106.15236","title":"New Arabic Medical Dataset for Diseases Classification","created":"2021-06-29","cited_by_count":0,"area":null},{"id":"2201.07434","title":"Interpreting Arabic Transformer Models","created":"2022-01-19","cited_by_count":0,"area":null},{"id":"2201.09227","title":"A Large and Diverse Arabic Corpus for Language Modeling","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2308.14669","title":"ANER: Arabic and Arabizi Named Entity Recognition using Transformer-Based Approach","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2312.16104","title":"Dotless Representation of Arabic Text: Analysis and Modeling","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2606.24758","title":"CANDLE: CTC-based Arabic Noisy-character Deduplication using a Lightweight Encoder","created":"2026-06-23","cited_by_count":0,"area":null}],"next_cursor":null}