{"total":41,"rows":[{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"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":"2103.08466","title":"NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task","created":"2021-03-04","cited_by_count":32,"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":"2306.05871","title":"Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?","created":"2023-06-09","cited_by_count":23,"area":null},{"id":"2110.06744","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","created":"2021-10-13","cited_by_count":20,"area":null},{"id":"2311.03179","title":"ArAIEval Shared Task: Persuasion Techniques and Disinformation Detection in Arabic Text","created":"2023-11-06","cited_by_count":19,"area":null},{"id":"2311.09812","title":"Large Language Models for Propaganda Span Annotation","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2410.20238","title":"A Survey of Large Language Models for Arabic Language and its Dialects","created":"2024-10-26","cited_by_count":13,"area":null},{"id":"2302.03512","title":"A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends","created":"2023-02-07","cited_by_count":8,"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":"2402.15313","title":"ArabianGPT: Native Arabic GPT-based Large Language Model","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2412.11431","title":"Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2103.01679","title":"AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment Detection in Arabic Tweets","created":"2021-03-02","cited_by_count":4,"area":null},{"id":"2205.06025","title":"DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2212.13939","title":"Data Augmentation using Transformers and Similarity Measures for Improving Arabic Text Classification","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2408.12362","title":"CLEANANERCorp: Identifying and Correcting Incorrect Labels in the ANERcorp Dataset","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2505.23276","title":"The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2303.09823","title":"Transformers and Ensemble methods: A solution for Hate Speech Detection in Arabic languages","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2508.06971","title":"Two-Stage Quranic QA via Ensemble Retrieval and Instruction-Tuned Answer Extraction","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2102.09749","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT","created":"2021-02-19","cited_by_count":1,"area":null},{"id":"2210.09990","title":"Post-hoc analysis of Arabic transformer models","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2309.00246","title":"Detecting Suicidality in Arabic Tweets Using Machine Learning and Deep Learning Techniques","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2407.02448","title":"Ensemble of pre-trained language models and data augmentation for hate speech detection from Arabic tweets","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2504.21475","title":"Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2507.23404","title":"Enhanced Arabic Text Retrieval with Attentive Relevance Scoring","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2511.13335","title":"AHaSIS: Shared Task on Sentiment Analysis for Arabic Dialects","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2111.05671","title":"Pre-trained Transformer-Based Approach for Arabic Question Answering : A Comparative Study","created":"2021-11-10","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":"2210.08209","title":"Large Language Models for Multi-label Propaganda Detection","created":"2022-10-15","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":"2501.05476","title":"IntegrityAI at GenAI Detection Task 2: Detecting Machine-Generated Academic Essays in English and Arabic Using ELECTRA and Stylometry","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2507.21095","title":"QU-NLP at CheckThat! 2025: Multilingual Subjectivity in News Articles Detection using Feature-Augmented Transformer Models with Sequential Cross-Lingual Fine-Tuning","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2509.10040","title":"!MSA at BAREC Shared Task 2025: Ensembling Arabic Transformers for Readability Assessment","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2509.23515","title":"From Human Annotation to Automation: LLM-in-the-Loop Active Learning for Arabic Sentiment Analysis","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.03502","title":"ALHD: A Large-Scale and Multigenre Benchmark Dataset for Arabic LLM-Generated Text Detection","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.20610","title":"BUSTED at AraGenEval Shared Task: A Comparative Study of Transformer-Based Models for Arabic AI-Generated Text Detection","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.21512","title":"MURAD: A Large-Scale Multi-Domain Unified Reverse Arabic Dictionary Dataset","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2607.08362","title":"Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}