{"total":55,"rows":[{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","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":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"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":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"area":null},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"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":"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":"2502.18795","title":"Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2402.10712","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","created":"2024-02-16","cited_by_count":18,"area":null},{"id":"2310.14201","title":"Prompt Engineering Through the Lens of Optimal Control","created":"2023-10-22","cited_by_count":16,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2401.16640","title":"TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese","created":"2024-01-30","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":"2208.05909","title":"Domain-Specific Text Generation for Machine Translation","created":"2022-08-11","cited_by_count":12,"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":"2301.10439","title":"ViDeBERTa: A powerful pre-trained language model for Vietnamese","created":"2023-01-25","cited_by_count":11,"area":null},{"id":"2110.08554","title":"PAGnol: An Extra-Large French Generative Model","created":"2021-10-16","cited_by_count":9,"area":null},{"id":"2312.01314","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2510.13430","title":"Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps","created":"2025-10-15","cited_by_count":9,"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":"2403.12392","title":"AraPoemBERT: A Pretrained Language Model for Arabic Poetry Analysis","created":"2024-03-19","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":"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":"2311.07497","title":"Multilingual Nonce Dependency Treebanks: Understanding how Language Models represent and process syntactic structure","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2405.14277","title":"Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2407.11212","title":"Automated essay scoring in Arabic: a dataset and analysis of a BERT-based system","created":"2024-07-15","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":"2507.22603","title":"BALSAM: A Platform for Benchmarking Arabic Large Language Models","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2406.10878","title":"Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions","created":"2024-06-16","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":"2401.14559","title":"Language Modelling Approaches to Adaptive Machine Translation","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2212.08514","title":"Check-worthy Claim Detection across Topics for Automated Fact-checking","created":"2022-12-16","cited_by_count":2,"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":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.13525","title":"Saudi-Dialect-ALLaM: LoRA Fine-Tuning for Dialectal Arabic Generation","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.18514","title":"A Rhythm-Aware Phrase Insertion for Classical Arabic Poetry Composition","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2511.14295","title":"AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2604.21108","title":"Machine learning and emoji prediction: How much accuracy can MARBERT achieve?","created":"2026-04-22","cited_by_count":2,"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":"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":"2309.12863","title":"Domain Adaptation for Arabic Machine Translation: The Case of Financial Texts","created":"2023-09-22","cited_by_count":1,"area":null},{"id":"2412.04277","title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2503.13101","title":"Who Wrote This? Identifying Machine vs Human-Generated Text in Hausa","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2507.19699","title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2602.09826","title":"From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models","created":"2026-02-10","cited_by_count":1,"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":"2609.14571","title":"Domain-specific Pretraining Profile and Transformer Performance: Evidence from Modeling Digital Pragmatics in Arabic-English Code-switching","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.00223","title":"A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.02529","title":"A generative-informed neuro-symbolic framework for syntactic ambiguity resolution: Evidence from Arabic DPs","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}