{"total":26,"rows":[{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2402.11968","title":"What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects","created":"2024-02-19","cited_by_count":21,"area":null},{"id":"2304.09805","title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","created":"2023-04-19","cited_by_count":16,"area":null},{"id":"2505.12158","title":"The AI Gap: How Socioeconomic Status Affects Language Technology Interactions","created":"2025-05-17","cited_by_count":15,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2405.05376","title":"Krey\\`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages","created":"2024-05-08","cited_by_count":10,"area":null},{"id":"2310.19567","title":"CreoleVal: Multilingual Multitask Benchmarks for Creoles","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2305.06530","title":"How Good are Commercial Large Language Models on African Languages?","created":"2023-05-11","cited_by_count":8,"area":null},{"id":"2404.19442","title":"Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2411.12262","title":"Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2410.12691","title":"Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2503.03186","title":"Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2506.07506","title":"What Do Indonesians Really Need from Language Technology? A Nationwide Survey","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2212.06383","title":"Towards a general purpose machine translation system for Sranantongo","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2504.06669","title":"NLP Security and Ethics, in the Wild","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2507.03473","title":"Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2405.03832","title":"Guylingo: The Republic of Guyana Creole Corpora","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2408.04554","title":"Moly\\'e: A Corpus-based Approach to Language Contact in Colonial France","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2503.06547","title":"Kr\\'eyoLID From Language Identification Towards Language Mining","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2504.05009","title":"Deconstructing Jazz Piano Style Using Machine Learning","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.24525","title":"Limited-Resource Adapters Are Regularizers, Not Linguists","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2604.11803","title":"Saar-Voice: A Multi-Speaker Saarbr\\\"ucken Dialect Speech Corpus","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2608.30866","title":"Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.13615","title":"The University of Melbourne WMT 2026 CreoleMT Submission: A Domain-Balanced Approach to Low-Resource Pacific Creole Machine Translation","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}