{"total":362,"rows":[{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"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":"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":"2101.00204","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","created":"2021-01-01","cited_by_count":125,"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":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"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":"2109.12068","title":"AraT5: Text-to-Text Transformers for Arabic Language Generation","created":"2021-08-31","cited_by_count":63,"area":null},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"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":"2203.13240","title":"Token Dropping for Efficient BERT Pretraining","created":"2022-03-24","cited_by_count":42,"area":"inference"},{"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":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"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":"2103.08466","title":"NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task","created":"2021-03-04","cited_by_count":32,"area":null},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2306.07933","title":"Understanding Telecom Language Through Large Language Models","created":"2023-06-09","cited_by_count":32,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"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":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2108.11193","title":"Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens","created":"2021-08-25","cited_by_count":27,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25,"area":null},{"id":"2203.10945","title":"AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization","created":"2022-03-21","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":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"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":"2305.14989","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2402.17478","title":"Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles","created":"2024-02-27","cited_by_count":21,"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":"2403.17848","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","created":"2024-03-26","cited_by_count":20,"area":null},{"id":"2407.05841","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","created":"2024-07-08","cited_by_count":20,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2304.10158","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","created":"2023-04-20","cited_by_count":19,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"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":"2109.12346","title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect","created":"2021-09-25","cited_by_count":18,"area":null},{"id":"2205.09685","title":"ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSD","created":"2022-05-19","cited_by_count":18,"area":null},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2505.18152","title":"Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2103.10195","title":"Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language","created":"2021-03-18","cited_by_count":15,"area":null},{"id":"2203.09904","title":"Do Multilingual Language Models Capture Differing Moral Norms?","created":"2022-03-18","cited_by_count":15,"area":null},{"id":"2503.00151","title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2102.01909","title":"HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition","created":"2021-02-03","cited_by_count":14,"area":null},{"id":"2106.07540","title":"Evaluating Various Tokenizers for Arabic Text Classification","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2109.07348","title":"Cross-lingual Transfer of Monolingual Models","created":"2021-09-15","cited_by_count":14,"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":"2110.06852","title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects","created":"2021-10-13","cited_by_count":14,"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":"2205.10517","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","created":"2022-05-21","cited_by_count":14,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2204.04748","title":"Breaking Character: Are Subwords Good Enough for MRLs After All?","created":"2022-04-10","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":"2105.02388","title":"Security Vulnerability Detection Using Deep Learning Natural Language Processing","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2106.12488","title":"Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language","created":"2021-06-23","cited_by_count":12,"area":null},{"id":"2506.01340","title":"The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technology","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2109.15254","title":"SlovakBERT: Slovak Masked Language Model","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2110.13658","title":"Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?","created":"2021-10-26","cited_by_count":11,"area":null},{"id":"2202.13558","title":"CINO: A Chinese Minority Pre-trained Language Model","created":"2022-02-28","cited_by_count":11,"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":"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":"2305.06074","title":"iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"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":"2301.04535","title":"Few-shot Learning for Cross-Target Stance Detection by Aggregating Multimodal Embeddings","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2307.07262","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","created":"2023-07-14","cited_by_count":9,"area":null},{"id":"2503.00985","title":"Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2109.03004","title":"Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge","created":"2021-09-07","cited_by_count":8,"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":"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":"2409.07246","title":"Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2502.00094","title":"AIN: The Arabic INclusive Large Multimodal Model","created":"2025-01-31","cited_by_count":8,"area":"mllm"},{"id":"2502.13520","title":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2502.16550","title":"PropXplain: Can LLMs Enable Explainable Propaganda Detection?","created":"2025-02-23","cited_by_count":8,"area":null},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2506.02280","title":"The State of Large Language Models for African Languages: Progress and Challenges","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2103.04353","title":"Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data","created":"2021-03-07","cited_by_count":7,"area":null},{"id":"2205.02211","title":"User-Centric Gender Rewriting","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2210.08284","title":"AraLegal-BERT: A pretrained language model for Arabic Legal text","created":"2022-10-15","cited_by_count":7,"area":null},{"id":"2210.11359","title":"Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2211.00171","title":"Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats","created":"2022-10-31","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":"2310.17333","title":"Arabic Fine-Grained Entity Recognition","created":"2023-10-26","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":"2405.06239","title":"SaudiBERT: A Large Language Model Pretrained on Saudi Dialect Corpora","created":"2024-05-10","cited_by_count":7,"area":null},{"id":"2507.04569","title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","created":"2025-07-06","cited_by_count":7,"area":null}],"next_cursor":"100"}