{"total":34,"rows":[{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"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":"2401.01055","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","created":"2024-01-02","cited_by_count":95,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"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":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2406.08641","title":"ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets","created":"2024-06-12","cited_by_count":27,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2310.05513","title":"Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond","created":"2023-10-09","cited_by_count":10,"area":null},{"id":"2510.10159","title":"BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data","created":"2025-10-11","cited_by_count":10,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2309.10661","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2504.05898","title":"Assessing Thai Dialect Performance in LLMs with Automatic Benchmarks and Human Evaluation","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2306.14866","title":"Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2409.08564","title":"Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia","created":"2024-09-13","cited_by_count":4,"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":"2311.00958","title":"IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2505.10596","title":"Inclusivity of AI Speech in Healthcare: A Decade Look Back","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2306.14517","title":"Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2410.23133","title":"Crowdsourcing Lexical Diversity","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2507.22159","title":"IndoPref: A Multi-Domain Pairwise Preference Dataset for Indonesian","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2509.25878","title":"ASR Under Noise: Exploring Robustness for Sundanese and Javanese","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2310.11258","title":"Utilizing Weak Supervision To Generate Indonesian Conservation Dataset","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2311.00998","title":"Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2403.01817","title":"NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2507.03378","title":"Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2509.05060","title":"Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2604.27439","title":"Sentiment Analysis of AI Adoption in Indonesian Higher Education Using Machine Learning and Transformer-Based Models","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.17442","title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.28715","title":"SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages","created":"2026-06-27","cited_by_count":0,"area":null}],"next_cursor":null}