{"total":41,"rows":[{"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,"area":null},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"area":null},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2510.11254","title":"Do Psychometric Tests Work for Large Language Models? Evaluation of Tests on Sexism, Racism, and Morality","created":"2025-10-13","cited_by_count":9,"area":null},{"id":"2410.01811","title":"Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English","created":"2024-09-14","cited_by_count":8,"area":null},{"id":"2501.02039","title":"An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage","created":"2025-01-03","cited_by_count":8,"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":"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":"2410.10489","title":"Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation","created":"2024-10-14","cited_by_count":7,"area":null},{"id":"2504.05325","title":"Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models","created":"2025-03-16","cited_by_count":7,"area":null},{"id":"2601.07972","title":"Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2502.05467","title":"Position: LLMs Can be Good Tutors in English Education","created":"2025-02-08","cited_by_count":6,"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":"2505.21362","title":"Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2507.21319","title":"Do Large Language Models Understand Morality Across Cultures?","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2510.11563","title":"Culturally-Aware Conversations: A Framework & Benchmark for LLMs","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2501.16748","title":"Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2509.25897","title":"RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2412.00962","title":"LLMs as mirrors of societal moral standards: reflection of cultural divergence and agreement across ethical topics","created":"2024-12-01","cited_by_count":3,"area":null},{"id":"2502.18583","title":"What are Foundation Models Cooking in the Post-Soviet World?","created":"2025-02-25","cited_by_count":3,"area":null},{"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":"2506.12433","title":"Exploring Cultural Variations in Moral Judgments with Large Language Models","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2604.21564","title":"Measuring Opinion Bias and Sycophancy via LLM-based Persuasion","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2506.13245","title":"A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.03247","title":"Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2512.10065","title":"Linear socio-demographic representations emerge in Large Language Models from indirect cues","created":"2025-12-10","cited_by_count":2,"area":null},{"id":"2603.01211","title":"A Unified Framework to Quantify Cultural Intelligence of AI","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2506.21587","title":"A Cross-Cultural Comparison of LLM-based Public Opinion Simulation: Evaluating Chinese and U.S. Models on Diverse Societies","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2605.16193","title":"Improving Cross-Cultural Survey Simulation with Calibrated Value Personas","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2609.01902","title":"Accurate in space, unreliable in time: how LLMs represent national cultural change","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2505.01967","title":"Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2509.11921","title":"Designing LLMs for cultural sensitivity: Evidence from English-Japanese translation","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2602.08121","title":"Initial Risk Probing and Feasibility Testing of Glow: a Generative AI-Powered Dialectical Behavior Therapy Skills Coach for Substance Use Recovery and HIV Prevention","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2608.12341","title":"The \"Knowledge-Behavior Gap\" in Cultural Taboo Safety of Large Language Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2609.16006","title":"Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.20059","title":"AI Should Facilitate Democratic Deliberation at Scale","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.15732","title":"NepPlural: A Human-Anchored Benchmark for Persona Annotation in Nepali Migration Discourse","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}