{"total":20,"rows":[{"id":"2311.05640","title":"FinGPT: Large Generative Models for a Small Language","created":"2023-11-03","cited_by_count":49,"area":null},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2404.01856","title":"Poro 34B and the Blessing of Multilinguality","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2107.12930","title":"gaBERT -- an Irish Language Model","created":"2021-07-27","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":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2102.11278","title":"RUBERT: A Bilingual Roman Urdu BERT Using Cross Lingual Transfer Learning","created":"2021-02-22","cited_by_count":6,"area":null},{"id":"2108.01139","title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","created":"2021-08-02","cited_by_count":6,"area":null},{"id":"2603.29552","title":"Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2109.04098","title":"ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2102.10958","title":"Bilingual Language Modeling, A transfer learning technique for Roman Urdu","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2303.13355","title":"Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension","created":"2023-03-16","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":"2602.04659","title":"Approaches to Semantic Textual Similarity in Slovak Language: From Algorithms to Transformers","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.05624","title":"YoNER: A New Yor\\`ub\\'a Multi-domain Named Entity Recognition Dataset","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2609.21362","title":"Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}