{"total":61,"rows":[{"id":"2406.04770","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","created":"2024-06-07","cited_by_count":218,"area":null},{"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":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2412.04862","title":"EXAONE 3.5: Series of Large Language Models for Real-world Use Cases","created":"2024-12-06","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"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":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"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":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"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":"2403.01469","title":"KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations","created":"2024-03-03","cited_by_count":22,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2404.01954","title":"HyperCLOVA X Technical Report","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2404.13919","title":"Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models","created":"2024-04-22","cited_by_count":15,"area":null},{"id":"2411.05049","title":"ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding","created":"2024-11-07","cited_by_count":15,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2412.17933","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2406.07736","title":"MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2403.12675","title":"Pragmatic Competence Evaluation of Large Language Models for the Korean Language","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2501.02266","title":"LLMzSz{\\L}: a comprehensive LLM benchmark for Polish","created":"2025-01-04","cited_by_count":7,"area":null},{"id":"2505.18951","title":"BnMMLU: Measuring Massive Multitask Language Understanding in Bengali","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2602.06221","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2504.15431","title":"Trillion 7B Technical Report","created":"2025-04-21","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":"2506.00482","title":"Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2508.16185","title":"ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects","created":"2025-08-22","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":"2502.15422","title":"Evaluating Multimodal Generative AI with Korean Educational Standards","created":"2025-02-21","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":"2507.05686","title":"Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2509.03972","title":"Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2510.14565","title":"Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.21193","title":"Estonian Native Large Language Model Benchmark","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2503.22968","title":"Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2507.06795","title":"ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.02635","title":"Test Set Quality in Multilingual LLM Evaluation","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.14913","title":"Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2604.14634","title":"Pushing the Boundaries of Multiple Choice Evaluation to One Hundred Options","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2405.15640","title":"GECKO: Generative Language Model for English, Code and Korean","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2504.13216","title":"KFinEval-Pilot: A Comprehensive Benchmark Suite for Korean Financial Language Understanding","created":"2025-04-17","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":"2507.04329","title":"No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2510.15558","title":"KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.04693","title":"Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.13058","title":"KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.25297","title":"LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.10391","title":"Phoenix-VL 1.5 Medium Technical Report","created":"2026-05-11","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":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.12433","title":"Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.04397","title":"NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.30229","title":"Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models","created":"2026-08-31","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}