{"total":66,"rows":[{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173,"area":null},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98,"area":null},{"id":"2501.02448","title":"Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap","created":"2025-01-05","cited_by_count":43,"area":"lr"},{"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":"2411.02460","title":"Code-Switching Curriculum Learning for Multilingual Transfer in LLMs","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2406.16469","title":"Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration","created":"2024-06-24","cited_by_count":19,"area":"mllm"},{"id":"2404.01954","title":"HyperCLOVA X Technical Report","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2505.16125","title":"KoBALT: Korean Benchmark For Advanced Linguistic Tasks","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2406.04215","title":"mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans","created":"2024-06-06","cited_by_count":10,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2412.07251","title":"KULTURE Bench: A Benchmark for Assessing Language Model in Korean Cultural Context","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2502.07459","title":"PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian","created":"2025-02-11","cited_by_count":8,"area":null},{"id":"2503.17485","title":"SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia","created":"2025-03-21","cited_by_count":8,"area":null},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2507.04014","title":"Nunchi-Bench: Benchmarking Language Models on Cultural Reasoning with a Focus on Korean Superstition","created":"2025-07-05","cited_by_count":6,"area":"lr"},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2410.18436","title":"Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2510.08608","title":"MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2601.03481","title":"Self-Explaining Hate Speech Detection with Moral Rationales","created":"2026-01-07","cited_by_count":5,"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":"2507.05820","title":"Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents","created":"2025-07-08","cited_by_count":4,"area":"agents"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2504.01127","title":"Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2505.21092","title":"BLUCK: A Benchmark Dataset for Bengali Linguistic Understanding and Cultural Knowledge","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2505.24409","title":"When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"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":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","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":"2606.02404","title":"K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2506.01237","title":"Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.04693","title":"Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification","created":"2025-06-05","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":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.07022","title":"Solar Open Technical Report","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2502.07455","title":"RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation","created":"2025-02-11","cited_by_count":1,"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":"2509.04432","title":"Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki","created":"2025-09-04","cited_by_count":1,"area":"lr"},{"id":"2509.17807","title":"Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2510.19616","title":"PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2602.03709","title":"No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.15949","title":"BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.21086","title":"LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2504.05995","title":"NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge","created":"2025-04-08","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":"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":"2601.02641","title":"An Empirical Study of On-Device Translation for Real-Time Live-Stream Chat on Mobile Devices","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.04632","title":"From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2602.09444","title":"Conceptual Cultural Index: A Metric for Cultural Specificity via Relative Generality","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.08275","title":"AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.18788","title":"Mi:dm K 2.5 Pro","created":"2026-03-19","cited_by_count":0,"area":"agents"},{"id":"2603.27563","title":"InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection","created":"2026-03-29","cited_by_count":0,"area":"agents"},{"id":"2604.19782","title":"KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.25676","title":"CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG","created":"2026-04-28","cited_by_count":0,"area":"rag"},{"id":"2605.02601","title":"SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures","created":"2026-05-04","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":"2606.27595","title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.00724","title":"MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark","created":"2026-07-01","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":"2608.04505","title":"K-EXAONE 2.0 Technical Report","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.30181","title":"A.X K2 Technical Report","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"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":"2610.20472","title":"ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}