{"total":54,"rows":[{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2507.09650","title":"Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset","created":"2025-07-13","cited_by_count":35,"area":"alignment"},{"id":"2509.01063","title":"An Economy of AI Agents","created":"2025-09-01","cited_by_count":18,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2505.21548","title":"Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2505.23785","title":"Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2506.00751","title":"Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2505.00174","title":"Real-World Gaps in AI Governance Research","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2510.19733","title":"Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning","created":"2025-10-22","cited_by_count":5,"area":null},{"id":"2507.04395","title":"SpiritRAG: A Q&A System for Religion and Spirituality in the United Nations Archive","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2602.09416","title":"Are Language Models Sensitive to Morally Irrelevant Distractors?","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","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":"2605.13339","title":"Probing Persona-Dependent Preferences in Language Models","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2505.09289","title":"Reproducibility Study of \"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents\"","created":"2025-05-14","cited_by_count":2,"area":"agents"},{"id":"2507.00439","title":"Improving the Distributional Alignment of LLMs using Supervision","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2510.14014","title":"CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Models","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2603.05723","title":"Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.08797","title":"Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2504.14105","title":"Amplify Initiative: Building A Localized Data Platform for Globalized AI","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2509.11967","title":"MillStone: How Open-Minded Are LLMs?","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.12689","title":"From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2511.03180","title":"BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture","created":"2025-11-05","cited_by_count":1,"area":"lr"},{"id":"2603.04217","title":"When Do Language Models Endorse Limitations on Human Rights Principles?","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.03493","title":"Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2606.12730","title":"Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2607.20410","title":"LKValues: Aligning Large Language Models with Sri Lankan Societal Values","created":"2026-07-22","cited_by_count":1,"area":"alignment"},{"id":"2608.29266","title":"Measurement Validity in LLM Cultural Alignment","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2512.00009","title":"Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2512.05176","title":"Towards A Cultural Intelligence and Values Inferences Quality Benchmark for Community Values and Common Knowledge","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.17096","title":"Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2602.10964","title":"Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.11305","title":"Are Aligned Large Language Models Still Misaligned?","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"id":"2603.06264","title":"Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2604.04732","title":"Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.25654","title":"Progressing beyond Art Masterpieces or Touristic Clich\\'es: how to assess your LLMs for cultural alignment?","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.08486","title":"Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.10843","title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2605.30934","title":"Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under Ambiguity","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.03110","title":"Coherence Maximization Improves Pluralistic Alignment","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2607.05405","title":"CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queries","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.06955","title":"Critical Acclaim Orientation in Large Language Models: Evidence from Film Preference Elicitation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.09937","title":"Carefully Considering Culture: Analyzing LLM Alignment in Single- and Multi-Cultural Settings using Cultural Consensus Theory","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.29209","title":"Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.00999","title":"Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05993","title":"Alignment by Stereotyping: How LLMs Sacrifice Individual Distinctiveness for Cultural Adaptation","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}