{"list":"other","total":64,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"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},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120},{"id":"1908.09369","title":"On Measuring and Mitigating Biased Inferences of Word Embeddings","created":"2019-08-25","cited_by_count":112},{"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":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"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":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94},{"id":"2306.11247","title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety","created":"2023-06-20","cited_by_count":86},{"id":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76},{"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":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55},{"id":"2305.11844","title":"AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia","created":"2023-05-19","cited_by_count":54},{"id":"2406.14805","title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions","created":"2024-06-21","cited_by_count":52},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49},{"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":"2404.12464","title":"NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models","created":"2024-04-18","cited_by_count":48},{"id":"2410.23252","title":"Evaluating Cultural and Social Awareness of LLM Web Agents","created":"2024-10-30","cited_by_count":45},{"id":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32},{"id":"2407.06863","title":"Beyond Aesthetics: Cultural Competence in Text-to-Image Models","created":"2024-07-09","cited_by_count":30},{"id":"2504.08863","title":"An Evaluation of Cultural Value Alignment in LLM","created":"2025-04-11","cited_by_count":28},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27},{"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},{"id":"2403.14651","title":"DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures","created":"2024-02-23","cited_by_count":24},{"id":"2211.13069","title":"Cultural Incongruencies in Artificial Intelligence","created":"2022-11-19","cited_by_count":21},{"id":"2401.10352","title":"Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys","created":"2024-01-18","cited_by_count":18},{"id":"2503.19075","title":"The Case for \"Thick Evaluations\" of Cultural Representation in AI","created":"2025-03-24","cited_by_count":17},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16},{"id":"2510.06124","title":"Taxonomy of User Needs and Actions","created":"2025-10-07","cited_by_count":15},{"id":"2502.14906","title":"Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models","created":"2025-02-18","cited_by_count":14},{"id":"2505.21693","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","created":"2025-05-27","cited_by_count":13},{"id":"2509.16188","title":"CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs","created":"2025-09-19","cited_by_count":12},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11},{"id":"2403.03909","title":"A Measure for Transparent Comparison of Linguistic Diversity in Multilingual NLP Data Sets","created":"2024-03-06","cited_by_count":10},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10},{"id":"2410.21596","title":"Chatbot Companionship: A Mixed-Methods Study of Companion Chatbot Usage Patterns and Their Relationship to Loneliness in Active Users","created":"2024-10-28","cited_by_count":8},{"id":"2505.21701","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","created":"2025-05-27","cited_by_count":8},{"id":"2501.02074","title":"A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI Evaluations","created":"2025-01-03","cited_by_count":7},{"id":"2511.12014","title":"CURE: Cultural Understanding and Reasoning Evaluation - A Framework for \"Thick\" Culture Alignment Evaluation in LLMs","created":"2025-11-15","cited_by_count":7},{"id":"2505.24712","title":"HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin America","created":"2025-05-30","cited_by_count":6},{"id":"2502.13497","title":"Towards Geo-Culturally Grounded LLM Generations","created":"2025-02-19","cited_by_count":5},{"id":"2510.11563","title":"Culturally-Aware Conversations: A Framework & Benchmark for LLMs","created":"2025-10-13","cited_by_count":5},{"id":"2503.05609","title":"Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity","created":"2025-03-07","cited_by_count":3},{"id":"2505.22793","title":"Evaluation of Cultural Competence of Vision-Language Models","created":"2025-05-28","cited_by_count":3},{"id":"2510.25167","title":"Scaling Cultural Resources for Improving Generative Models","created":"2025-10-29","cited_by_count":2},{"id":"2601.07973","title":"Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations","created":"2026-01-12","cited_by_count":2}],"next_cursor":null}