{"total":33,"rows":[{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","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":"2406.17363","title":"Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation","created":"2024-06-25","cited_by_count":9,"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":"2508.12459","title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2412.04003","title":"Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement","created":"2024-12-05","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":"2508.00673","title":"MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2508.15239","title":"WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2602.02266","title":"OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2412.18053","title":"Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2504.08792","title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2507.14664","title":"Mangosteen: An Open Thai Corpus for Language Model Pretraining","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2409.08523","title":"Eir: Thai Medical Large Language Models","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2505.02518","title":"Bemba Speech Translation: Exploring a Low-Resource African Language","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2508.08715","title":"MultiGen: Child-Friendly Multilingual Speech Generator with LLMs","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.17317","title":"Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2602.04764","title":"Beyond Many-Shot Translation: Scaling In-Context Demonstrations For Low-Resource Machine Translation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.18788","title":"BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models","created":"2026-02-21","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":"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":"2510.10776","title":"HiligayNER: A Baseline Named Entity Recognition Model for Hiligaynon","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2604.20720","title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","created":"2026-04-22","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":"2606.02493","title":"Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.15044","title":"Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models","created":"2026-06-13","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},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}