{"total":36,"rows":[{"id":"2603.11510","title":"Tiny Aya: Bridging Scale and Multilingual Depth","created":"2026-03-12","cited_by_count":15,"area":null},{"id":"2509.05486","title":"The Token Tax: Systematic Bias in Multilingual Tokenization","created":"2025-09-05","cited_by_count":14,"area":null},{"id":"2412.17933","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2609.37647","title":"Evaluating and Benchmarking the System One Model Jev","created":"2026-09-29","cited_by_count":9,"area":null},{"id":"2412.00948","title":"Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2504.06536","title":"Lugha-Llama: Adapting Large Language Models for African Languages","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2506.08400","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2505.18436","title":"Voice of a Continent: Mapping Africa's Speech Technology Frontier","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2503.11911","title":"LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2511.02752","title":"AI Diffusion in Low Resource Language Countries","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2601.05699","title":"Afri-MCQA: Multimodal Cultural Question Answering for African Languages","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.09373","title":"AfriNLLB: Efficient Translation Models for African Languages","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2504.13284","title":"Sentiment Analysis on the young people's perception about the mobile Internet costs in Senegal","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2412.12417","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2502.19784","title":"NaijaNLP: A Survey of Nigerian Low-Resource Languages","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2506.21563","title":"FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.22968","title":"Against 'softmaxing' culture","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2510.05644","title":"The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.07203","title":"Sunflower: A New Approach To Expanding Coverage of African Languages in Large Language Models","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.09716","title":"Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.17283","title":"Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.20732","title":"MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.16392","title":"RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.03590","title":"AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition","created":"2026-05-05","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":"2606.03304","title":"From Script to Semantics: Prompting Strategies for African NLI","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.18117","title":"Position: AI Leaderboards Are Underserving the Global South: A Case Study from India","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.18655","title":"TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.19003","title":"Structure, Association, and Decision Value: Representation-Based Difficulty Estimation for Adaptive Inference in African-Language NLI","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.23358","title":"The Geometry of Low-Resource Language Representations","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.17853","title":"AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18384","title":"GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}