{"total":84,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"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":"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":"2102.10684","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","created":"2021-02-21","cited_by_count":39,"area":null},{"id":"2101.10038","title":"SpanEmo: Casting Multi-label Emotion Classification as Span-prediction","created":"2021-01-25","cited_by_count":37,"area":null},{"id":"2103.13031","title":"Czert -- Czech BERT-like Model for Language Representation","created":"2021-03-24","cited_by_count":22,"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":"2305.14734","title":"Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation","created":"2023-05-24","cited_by_count":22,"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":"2105.15071","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2402.08638","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","created":"2024-02-13","cited_by_count":16,"area":null},{"id":"2109.12986","title":"Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection","created":"2021-09-23","cited_by_count":14,"area":null},{"id":"2210.15842","title":"Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion","created":"2022-10-28","cited_by_count":14,"area":null},{"id":"2204.03558","title":"Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic","created":"2022-04-07","cited_by_count":13,"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":"2407.04247","title":"ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content","created":"2024-07-05","cited_by_count":11,"area":null},{"id":"2104.08110","title":"LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation","created":"2021-04-16","cited_by_count":9,"area":null},{"id":"2206.00524","title":"Vietnamese Hate and Offensive Detection using PhoBERT-CNN and Social Media Streaming Data","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2212.00552","title":"An Effective Deployment of Contrastive Learning in Multi-label Text Classification","created":"2022-12-01","cited_by_count":9,"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":"2104.13559","title":"AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2404.02340","title":"Corpus Considerations for Annotator Modeling and Scaling","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2108.10640","title":"Are the Multilingual Models Better? Improving Czech Sentiment with Transformers","created":"2021-08-24","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":"2107.05684","title":"Accenture at CheckThat! 2021: Interesting claim identification and ranking with contextually sensitive lexical training data augmentation","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2107.09186","title":"Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions","created":"2021-07-19","cited_by_count":6,"area":null},{"id":"2309.05951","title":"Balanced and Explainable Social Media Analysis for Public Health with Large Language Models","created":"2023-09-12","cited_by_count":6,"area":null},{"id":"2311.08669","title":"On the Calibration of Multilingual Question Answering LLMs","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2103.04386","title":"Automatic Difficulty Classification of Arabic Sentences","created":"2021-03-07","cited_by_count":5,"area":null},{"id":"2312.01339","title":"ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications","created":"2023-12-03","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":"2408.03524","title":"EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora","created":"2024-08-07","cited_by_count":5,"area":null},{"id":"2310.12892","title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2112.04329","title":"JABER and SABER: Junior and Senior Arabic BERt","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2204.09292","title":"Towards Arabic Sentence Simplification via Classification and Generative Approaches","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2308.03782","title":"Bio+Clinical BERT, BERT Base, and CNN Performance Comparison for Predicting Drug-Review Satisfaction","created":"2023-08-02","cited_by_count":3,"area":null},{"id":"2102.05708","title":"Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2105.13959","title":"Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments","created":"2021-05-28","cited_by_count":2,"area":null},{"id":"2107.02416","title":"Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings","created":"2021-07-06","cited_by_count":2,"area":null},{"id":"2110.05133","title":"Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2111.00611","title":"R-BERT-CNN: Drug-target interactions extraction from biomedical literature","created":"2021-10-31","cited_by_count":2,"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":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2305.13302","title":"Language-Agnostic Bias Detection in Language Models with Bias Probing","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2305.16302","title":"Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages","created":"2023-05-25","cited_by_count":2,"area":"distill"},{"id":"2309.13731","title":"Arabic Sentiment Analysis with Noisy Deep Explainable Model","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2509.00457","title":"CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning","created":"2025-08-30","cited_by_count":2,"area":"lr"},{"id":"2107.13290","title":"Arabic aspect sentiment polarity classification using BERT","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2203.03542","title":"Fine-Tuning Approach for Arabic Offensive Language Detection System: BERT-Based Model","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2205.03114","title":"Arabic Fake News Detection Based on Deep Contextualized Embedding Models","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2205.05857","title":"Comparing Open Arabic Named Entity Recognition Tools","created":"2022-05-12","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":"2305.01050","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","created":"2023-05-01","cited_by_count":1,"area":null},{"id":"2403.14990","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2410.03979","title":"Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2506.10292","title":"Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages","created":"2025-06-12","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":"2608.26192","title":"Comparing Chunking and Embedding Strategies for Turkish RAG Systems","created":"2026-08-24","cited_by_count":1,"area":"rag"},{"id":"2106.12744","title":"An Automated Knowledge Mining and Document Classification System with Multi-model Transfer Learning","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2109.14456","title":"Overview of the Arabic Sentiment Analysis 2021 Competition at KAUST","created":"2021-09-29","cited_by_count":0,"area":null},{"id":"2109.14816","title":"COVID-19 Fake News Detection Using Bidirectional Encoder Representations from Transformers Based Models","created":"2021-09-30","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":"2203.02123","title":"Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks","created":"2022-03-04","cited_by_count":0,"area":null},{"id":"2204.02263","title":"Multilingual and Multimodal Abuse Detection","created":"2022-04-03","cited_by_count":0,"area":null},{"id":"2204.10519","title":"Taygete at SemEval-2022 Task 4: RoBERTa based models for detecting Patronising and Condescending Language","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2205.08024","title":"Harnessing Multilingual Resources to Question Answering in Arabic","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2301.05863","title":"Detecting Stance of Authorities towards Rumors in Arabic Tweets: A Preliminary Study","created":"2023-01-14","cited_by_count":0,"area":null},{"id":"2304.00636","title":"Classifying COVID-19 Related Tweets for Fake News Detection and Sentiment Analysis with BERT-based Models","created":"2023-04-02","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":"2403.02975","title":"A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2404.01805","title":"Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2407.13097","title":"AlcLaM: Arabic Dialectal Language Model","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2506.02753","title":"Multi-task Learning with Active Learning for Arabic Offensive Speech Detection","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.23661","title":"Arabic Hate Speech Identification and Masking in Social Media using Deep Learning Models and Pre-trained Models Fine-tuning","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.16788","title":"Domain-Adaptive Pre-Training for Arabic Aspect-Based Sentiment Analysis: A Comparative Study of Domain Adaptation and Fine-Tuning Strategies","created":"2025-09-20","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":"2512.19543","title":"Algerian Dialect","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2609.38820","title":"BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic Dialects","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}