{"total":45,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120,"area":null},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167,"area":null},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91,"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":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2402.17302","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","created":"2024-02-27","cited_by_count":36,"area":null},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2504.15521","title":"The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks","created":"2025-04-22","cited_by_count":31,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2504.10356","title":"MultiLoKo: a multilingual local knowledge benchmark for LLMs spanning 31 languages","created":"2025-04-14","cited_by_count":26,"area":null},{"id":"2406.07302","title":"BertaQA: How Much Do Language Models Know About Local Culture?","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2406.11661","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"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":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2403.09362","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","created":"2024-03-14","cited_by_count":10,"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":"2504.17720","title":"Multilingual Performance Biases of Large Language Models in Education","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2502.09637","title":"Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness","created":"2025-02-09","cited_by_count":8,"area":null},{"id":"2506.02573","title":"IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2502.12829","title":"KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan","created":"2025-02-18","cited_by_count":6,"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":"2601.11778","title":"Translation as a Scalable Proxy for Multilingual Evaluation","created":"2026-01-16","cited_by_count":6,"area":null},{"id":"2506.00288","title":"Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2507.01785","title":"MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining","created":"2025-07-02","cited_by_count":5,"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":"2501.08335","title":"MERaLiON-TextLLM: Cross-Lingual Understanding of Large Language Models in Chinese, Indonesian, Malay, and Singlish","created":"2024-12-21","cited_by_count":4,"area":null},{"id":"2505.18638","title":"Multilingual Question Answering in Low-Resource Settings: A Dzongkha-English Benchmark for Foundation Models","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2505.16591","title":"Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering","created":"2025-05-22","cited_by_count":3,"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":"2608.25089","title":"Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation","created":"2026-08-25","cited_by_count":3,"area":null},{"id":"2403.08046","title":"Big City Bias: Evaluating the Impact of Metropolitan Size on Computational Job Market Abilities of Language Models","created":"2024-03-12","cited_by_count":2,"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":"2504.01667","title":"Testing Low-Resource Language Support in LLMs Using Language Proficiency Exams: the Case of Luxembourgish","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2603.27223","title":"EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.00923","title":"Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2601.12921","title":"Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2605.15613","title":"Toward LLMs Beyond English-Centric Development","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.28163","title":"DEPART: DEcomposing PARiTy across Multilingual LLMs","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.07167","title":"UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.18336","title":"Measuring the Partial-Credit Gap: A Strict Benchmark on Vietnam's 2025 Convex Marking Scheme","created":"2026-08-18","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},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}