{"total":20,"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":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"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":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2303.00069","title":"ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus","created":"2023-02-28","cited_by_count":14,"area":null},{"id":"2201.10066","title":"Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources","created":"2022-01-25","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2208.00932","title":"Masader Plus: A New Interface for Exploring +500 Arabic NLP Datasets","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2501.16516","title":"How well can LLMs Grade Essays in Arabic?","created":"2025-01-27","cited_by_count":6,"area":null},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2405.11282","title":"Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets","created":"2024-05-18","cited_by_count":4,"area":null},{"id":"2301.02521","title":"SAIDS: A Novel Approach for Sentiment Analysis Informed of Dialect and Sarcasm","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2207.10524","title":"NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2210.12985","title":"Maknuune: A Large Open Palestinian Arabic Lexicon","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2302.12299","title":"In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2510.06889","title":"MeXtract: Light-Weight Metadata Extraction from Scientific Papers","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2412.15259","title":"GLARE: Google Apps Arabic Reviews Dataset","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2605.20960","title":"JobArabi: An Arabic Corpus and Analysis of Job Announcements from Social Media","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":null}