{"total":31,"rows":[{"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":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68,"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":"2409.18472","title":"URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"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":"2403.13737","title":"EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2410.10489","title":"Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation","created":"2024-10-14","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":"2507.03003","title":"Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2308.09768","title":"NaijaRC: A Multi-choice Reading Comprehension Dataset for Nigerian Languages","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2406.12634","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2505.02463","title":"Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2410.08728","title":"From N-grams to Pre-trained Multilingual Models For Language Identification","created":"2024-10-11","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":"2504.00289","title":"Do Chinese models speak Chinese languages?","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2505.14311","title":"HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2507.17974","title":"Natural Language Processing for Tigrinya: Current State and Future Directions","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2605.18232","title":"SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.28190","title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2609.32684","title":"Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2507.20718","title":"Uncertainty-driven Embedding Convolution","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.03529","title":"Mafoko: Structuring and Building Open Multilingual Terminologies for South African NLP","created":"2025-08-05","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":"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":"2605.04208","title":"Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages","created":"2026-05-05","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":"2607.13967","title":"DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.37861","title":"One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37882","title":"How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07026","title":"Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}