{"total":98,"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":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2306.01102","title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","created":"2023-06-01","cited_by_count":87,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46,"area":null},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","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":"2304.06845","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","created":"2023-04-13","cited_by_count":41,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2402.19167","title":"Teaching Large Language Models an Unseen Language on the Fly","created":"2024-02-29","cited_by_count":30,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"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":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","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":"2208.13078","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","created":"2022-08-27","cited_by_count":13,"area":null},{"id":"2409.00626","title":"Correcting FLORES Evaluation Dataset for Four African Languages","created":"2024-09-01","cited_by_count":13,"area":null},{"id":"2303.03750","title":"Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora","created":"2023-03-07","cited_by_count":12,"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":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12,"area":null},{"id":"2501.06374","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2211.00142","title":"TaTa: A Multilingual Table-to-Text Dataset for African Languages","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2305.09249","title":"xPQA: Cross-Lingual Product Question Answering across 12 Languages","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2405.19462","title":"Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2303.17972","title":"$\\varepsilon$ K\\'U <MASK>: Integrating Yor\\`ub\\'a cultural greetings into machine translation","created":"2023-03-31","cited_by_count":8,"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":"2312.16159","title":"Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages","created":"2023-12-26","cited_by_count":8,"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":"2407.04796","title":"Toucan: Many-to-Many Translation for 150 African Language Pairs","created":"2024-07-05","cited_by_count":8,"area":null},{"id":"2307.10188","title":"Several categories of Large Language Models (LLMs): A Short Survey","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2403.20088","title":"An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2404.02392","title":"Low-resource neural machine translation with morphological modeling","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2410.09948","title":"State of NLP in Kenya: A Survey","created":"2024-10-13","cited_by_count":7,"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":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2210.10692","title":"Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages","created":"2022-10-19","cited_by_count":6,"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":"2511.06531","title":"Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages","created":"2025-11-09","cited_by_count":6,"area":null},{"id":"2305.00606","title":"Low-Resourced Machine Translation for Senegalese Wolof Language","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2306.01382","title":"Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translation","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2312.15614","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","created":"2023-12-25","cited_by_count":5,"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":"2303.12582","title":"AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages","created":"2023-03-22","cited_by_count":4,"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":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","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":"2412.20218","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yor\\`ub\\'a Text","created":"2024-12-28","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"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":"2601.03168","title":"Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages","created":"2026-01-06","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":"2606.01322","title":"TukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages","created":"2026-05-31","cited_by_count":3,"area":"safety"},{"id":"2308.01785","title":"Lexicon and Rule-based Word Lemmatization Approach for the Somali Language","created":"2023-08-03","cited_by_count":2,"area":null},{"id":"2309.05311","title":"Analysing Cross-Lingual Transfer in Low-Resourced African Named Entity Recognition","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2405.00997","title":"The IgboAPI Dataset: Empowering Igbo Language Technologies through Multi-dialectal Enrichment","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2412.19522","title":"Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2503.22582","title":"Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2510.27672","title":"Culture Cartography: Mapping the Landscape of Cultural Knowledge","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2511.09197","title":"The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages","created":"2025-11-12","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":"2211.16703","title":"An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2305.03207","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2412.11203","title":"Task-Oriented Dialog Systems for the Senegalese Wolof Language","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2512.13552","title":"PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.22404","title":"SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2208.04568","title":"The Impact of Data Corruption on Named Entity Recognition for Low-resourced Languages","created":"2022-08-09","cited_by_count":0,"area":null},{"id":"2210.11599","title":"The VolcTrans System for WMT22 Multilingual Machine Translation Task","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2305.12480","title":"Is Translation Helpful? An Empirical Analysis of Cross-Lingual Transfer in Low-Resource Dialog Generation","created":"2023-05-21","cited_by_count":0,"area":null},{"id":"2308.13497","title":"Ngambay-French Neural Machine Translation (sba-Fr)","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2311.12179","title":"Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2405.11819","title":"Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2505.15069","title":"In-Domain African Languages Translation Using LLMs and Multi-armed Bandits","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.18905","title":"Building a Functional Machine Translation Corpus for Kpelle","created":"2025-05-24","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":"2506.03820","title":"Automatic Correction of Writing Anomalies in Hausa Texts","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.07471","title":"From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation","created":"2025-09-09","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":"2511.03880","title":"Evaluating Machine Translation Datasets for Low-Web Data Languages: A Gendered Lens","created":"2025-11-05","cited_by_count":0,"area":"safety"},{"id":"2511.09537","title":"NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages","created":"2025-11-12","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":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.14210","title":"Vavanagi: a Community-run Platform for Documentation of the Hula Language in Papua New Guinea","created":"2026-03-15","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":"2603.25222","title":"Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.02596","title":"An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.12477","title":"Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe","created":"2026-04-14","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":"2605.29741","title":"AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.25365","title":"Neural Machine Translation for Low-Resource Tangkhul--English","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.07629","title":"Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2610.18818","title":"Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}