{"total":38,"rows":[{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2307.01163","title":"Improving Language Plasticity via Pretraining with Active Forgetting","created":"2023-07-03","cited_by_count":43,"area":null},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2211.15613","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","created":"2022-11-28","cited_by_count":33,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2305.06897","title":"AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages","created":"2023-05-11","cited_by_count":23,"area":null},{"id":"2305.13989","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18,"area":null},{"id":"2305.13582","title":"Translation and Fusion Improves Zero-shot Cross-lingual Information Extraction","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2305.10971","title":"NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2406.07424","title":"MINERS: Multilingual Language Models as Semantic Retrievers","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2305.00090","title":"NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis","created":"2023-04-28","cited_by_count":10,"area":null},{"id":"2306.00253","title":"AfriNames: Most ASR models \"butcher\" African Names","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2307.16071","title":"\\`{I}r\\`{o}y\\`{i}nSpeech: A multi-purpose Yor\\`{u}b\\'{a} Speech Corpus","created":"2023-07-29","cited_by_count":7,"area":null},{"id":"2404.02261","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2310.09141","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2303.16985","title":"Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languages","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2603.13793","title":"GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2304.03952","title":"MphayaNER: Named Entity Recognition for Tshivenda","created":"2023-04-08","cited_by_count":2,"area":null},{"id":"2310.00679","title":"CebuaNER: A New Baseline Cebuano Named Entity Recognition Model","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2502.17364","title":"Bridging Gaps in Natural Language Processing for Yor\\`ub\\'a: A Systematic Review of a Decade of Progress and Prospects","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2511.10664","title":"Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2305.14913","title":"CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2308.14280","title":"FonMTL: Towards Multitask Learning for the Fon Language","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2403.14990","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2404.04759","title":"What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2502.16947","title":"Using Machine Learning to Detect Fraudulent SMSs in Chichewa","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2505.16814","title":"Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2509.19271","title":"WolBanking77: Wolof Banking Speech Intent Classification Dataset","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2601.06875","title":"An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialogue","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2603.29244","title":"The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languages","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.19066","title":"The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.22828","title":"A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.22274","title":"From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa","created":"2026-06-20","cited_by_count":0,"area":null}],"next_cursor":null}