{"list":"other","total":221,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2309.12053","title":"AceGPT, Localizing Large Language Models in Arabic","created":"2023-09-21","cited_by_count":75},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66},{"id":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60},{"id":"2404.16308","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","created":"2024-04-25","cited_by_count":60},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59},{"id":"2307.01370","title":"Multilingual Language Models are not Multicultural: A Case Study in Emotion","created":"2023-07-03","cited_by_count":54},{"id":"2305.14328","title":"Benchmarking Machine Translation with Cultural Awareness","created":"2023-05-23","cited_by_count":53},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53},{"id":"2502.07068","title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations","created":"2025-02-10","cited_by_count":53},{"id":"2405.04655","title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","created":"2024-05-07","cited_by_count":51},{"id":"2501.15463","title":"Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?","created":"2025-01-26","cited_by_count":51},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48},{"id":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47},{"id":"2309.02706","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","created":"2023-09-06","cited_by_count":47},{"id":"2404.18460","title":"Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in","created":"2024-04-29","cited_by_count":46},{"id":"2409.11404","title":"AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs","created":"2024-09-17","cited_by_count":46},{"id":"2210.14250","title":"Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature","created":"2022-10-25","cited_by_count":45},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45},{"id":"2410.23252","title":"Evaluating Cultural and Social Awareness of LLM Web Agents","created":"2024-10-30","cited_by_count":45},{"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},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39},{"id":"2410.12705","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","created":"2024-10-16","cited_by_count":39},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37},{"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},{"id":"2404.01247","title":"An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance","created":"2024-04-01","cited_by_count":36},{"id":"2311.01012","title":"COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances","created":"2023-11-02","cited_by_count":35},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34},{"id":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33},{"id":"2403.01031","title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","created":"2024-03-01","cited_by_count":32},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32},{"id":"2407.12402","title":"TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish","created":"2024-07-17","cited_by_count":32},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31},{"id":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30},{"id":"2404.06833","title":"Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge","created":"2024-04-10","cited_by_count":29},{"id":"2407.03791","title":"M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks","created":"2024-07-04","cited_by_count":27},{"id":"2411.02538","title":"MILU: A Multi-task Indic Language Understanding Benchmark","created":"2024-11-04","cited_by_count":27},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27},{"id":"2508.01710","title":"CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications","created":"2025-08-03","cited_by_count":27},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25},{"id":"2205.04022","title":"CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality","created":"2022-05-09","cited_by_count":24},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24},{"id":"2403.14651","title":"DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures","created":"2024-02-23","cited_by_count":24},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2310.17586","title":"Global Voices, Local Biases: Socio-Cultural Prejudices across Languages","created":"2023-10-26","cited_by_count":23},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22},{"id":"2305.14492","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","created":"2023-05-23","cited_by_count":22},{"id":"2410.14057","title":"Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs","created":"2024-10-17","cited_by_count":22},{"id":"2501.04662","title":"On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena","created":"2025-01-08","cited_by_count":22},{"id":"2211.16496","title":"TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages","created":"2022-11-29","cited_by_count":21},{"id":"2505.24671","title":"Multiple LLM Agents Debate for Equitable Cultural Alignment","created":"2025-05-30","cited_by_count":21},{"id":"2509.02550","title":"PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture","created":"2025-09-02","cited_by_count":21},{"id":"2205.05738","title":"DISARM: Detecting the Victims Targeted by Harmful Memes","created":"2022-05-11","cited_by_count":20},{"id":"2306.02475","title":"Modeling Cross-Cultural Pragmatic Inference with Codenames Duet","created":"2023-06-04","cited_by_count":20},{"id":"2402.10689","title":"Cultural Commonsense Knowledge for Intercultural Dialogues","created":"2024-02-16","cited_by_count":20},{"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},{"id":"2410.17250","title":"JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation","created":"2024-10-22","cited_by_count":19},{"id":"2411.03769","title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","created":"2024-11-06","cited_by_count":19},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18},{"id":"2401.10352","title":"Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys","created":"2024-01-18","cited_by_count":18},{"id":"2503.00231","title":"Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking","created":"2025-02-28","cited_by_count":18},{"id":"2402.03177","title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic","created":"2024-02-05","cited_by_count":17},{"id":"2410.17040","title":"Arabic Dataset for LLM Safeguard Evaluation","created":"2024-10-22","cited_by_count":17},{"id":"2502.13775","title":"VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare","created":"2025-02-19","cited_by_count":17},{"id":"2307.14031","title":"Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems","created":"2023-07-26","cited_by_count":16},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16},{"id":"2502.13766","title":"GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking","created":"2025-02-19","cited_by_count":16},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16},{"id":"2505.18152","title":"Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs","created":"2025-05-23","cited_by_count":16},{"id":"2505.24635","title":"Disentangling Language and Culture for Evaluating Multilingual Large Language Models","created":"2025-05-30","cited_by_count":16},{"id":"2506.15355","title":"SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture","created":"2025-06-18","cited_by_count":16},{"id":"2508.07414","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","created":"2025-08-10","cited_by_count":16},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15}],"next_cursor":"100"}