{"total":14,"rows":[{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2111.06053","title":"Improving Large-scale Language Models and Resources for Filipino","created":"2021-11-11","cited_by_count":20,"area":null},{"id":"2201.05601","title":"A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2211.07467","title":"Cracking Double-Blind Review: Authorship Attribution with Deep Learning","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2302.14494","title":"Text classification dataset and analysis for Uzbek language","created":"2023-02-28","cited_by_count":3,"area":null},{"id":"2308.15952","title":"Benchmarking Multilabel Topic Classification in the Kyrgyz Language","created":"2023-08-30","cited_by_count":3,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2506.00863","title":"L3Cube-MahaEmotions: A Marathi Emotion Recognition Dataset with Synthetic Annotations using CoTR prompting and Large Language Models","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2111.06971","title":"Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2205.11840","title":"Lutma: a Frame-Making Tool for Collaborative FrameNet Development","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2505.18995","title":"FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)","created":"2025-05-25","cited_by_count":0,"area":null}],"next_cursor":null}