{"total":111,"rows":[{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100,"area":null},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99,"area":"agents"},{"id":"2312.15198","title":"Do LLM Agents Exhibit Social Behavior?","created":"2023-12-23","cited_by_count":53,"area":"agents"},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2410.12428","title":"Conformity in Large Language Models","created":"2024-10-16","cited_by_count":34,"area":null},{"id":"2410.07991","title":"Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets","created":"2024-10-10","cited_by_count":31,"area":null},{"id":"2405.20956","title":"A Robot Walks into a Bar: Can Language Models Serve as Creativity Support Tools for Comedy? An Evaluation of LLMs' Humour Alignment with Comedians","created":"2024-05-31","cited_by_count":29,"area":null},{"id":"2504.08863","title":"An Evaluation of Cultural Value Alignment in LLM","created":"2025-04-11","cited_by_count":28,"area":null},{"id":"2502.04426","title":"The simulation of judgment in LLMs","created":"2025-02-06","cited_by_count":22,"area":null},{"id":"2510.22422","title":"Group size effects and collective misalignment in LLM multi-agent systems","created":"2025-10-25","cited_by_count":16,"area":"agents"},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"area":"alignment"},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2501.01031","title":"ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning","created":"2025-01-02","cited_by_count":10,"area":"rag"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2510.18774","title":"AI use in American newspapers is widespread, uneven, and rarely disclosed","created":"2025-10-21","cited_by_count":10,"area":null},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2409.03843","title":"Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2506.23111","title":"FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2507.00657","title":"Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity","created":"2025-07-01","cited_by_count":9,"area":"agents"},{"id":"2503.01030","title":"Language Models Predict Empathy Gaps Between Social In-groups and Out-groups","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2503.20062","title":"Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays","created":"2025-03-25","cited_by_count":6,"area":"alignment"},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2402.10436","title":"I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"id":"2411.19240","title":"How far can bias go? Tracing bias from pretraining data to alignment","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2504.19445","title":"Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.01924","title":"To Mask or to Mirror: Human-AI Alignment in Collective Reasoning","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"id":"2601.00240","title":"When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents","created":"2026-01-01","cited_by_count":5,"area":"agents"},{"id":"2602.04398","title":"Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2503.03335","title":"iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2505.17217","title":"Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2506.14159","title":"StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2503.22723","title":"Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping","created":"2025-03-26","cited_by_count":3,"area":"alignment"},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2507.00088","title":"How large language models judge and influence human cooperation","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2510.24831","title":"The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2603.15423","title":"Invisible failures in human-AI interactions","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2410.17333","title":"Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance","created":"2024-10-22","cited_by_count":2,"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":"2506.02431","title":"From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.13783","title":"Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2509.06858","title":"Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.26464","title":"Extreme Self-Preference in Language Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.21180","title":"Social Simulations with Large Language Model Risk Utopian Illusion","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.07871","title":"AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys","created":"2025-11-11","cited_by_count":2,"area":"alignment"},{"id":"2604.19548","title":"Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2605.01329","title":"Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents","created":"2026-05-02","cited_by_count":2,"area":"agents"},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","cited_by_count":2,"area":"agents"},{"id":"2609.00009","title":"Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2501.06461","title":"Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2503.05047","title":"Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.16480","title":"Human Preferences for Constructive Interactions in Language Model Alignment","created":"2025-03-05","cited_by_count":1,"area":"alignment"},{"id":"2505.20901","title":"A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language Models","created":"2025-05-27","cited_by_count":1,"area":"mllm"},{"id":"2506.20822","title":"Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.08837","title":"Debiasing International Attitudes: LLM Agents for Simulating US-China Perception Changes","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.15478","title":"Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models","created":"2025-09-18","cited_by_count":1,"area":"mllm"},{"id":"2509.20278","title":"Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2510.04528","title":"Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"id":"2510.13985","title":"Do Large Language Models Show Biases in Causal Learning? Insights from Contingency Judgment","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2602.16438","title":"Intra-Fairness Dynamics: The Bias Spillover Effect in Targeted LLM Alignment","created":"2026-02-18","cited_by_count":1,"area":"alignment"},{"id":"2603.22260","title":"Greater accessibility can amplify discrimination in generative AI","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.15937","title":"Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.16757","title":"Expressing Social Emotions: Misalignment Between LLMs and Human Cultural Emotion Norms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.17968","title":"From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.20048","title":"Culturally uneven urban perception in large language models","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.29062","title":"Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2609.33495","title":"LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2502.11809","title":"Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.10229","title":"R.U.Psycho? Robust Unified Psychometric Testing of Language Models","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.08902","title":"Performance Gains of LLMs With Humans in a World of LLMs Versus Humans","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2505.13302","title":"Images Amplify Misinformation Sharing in Vision-Language Models","created":"2025-05-19","cited_by_count":0,"area":"mllm"},{"id":"2506.12556","title":"Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2506.18045","title":"The Democratic Paradox in Large Language Models' Underestimation of Press Freedom","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2507.13175","title":"Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era","created":"2025-07-17","cited_by_count":0,"area":"agents"},{"id":"2510.05869","title":"The fragility of \"cultural tendencies\" in LLMs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.06974","title":"Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2511.20736","title":"Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.15792","title":"A Multifaceted Analysis of Social Biases in Large Language Models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.04730","title":"Automatic Classifiers Underdetect Emotions Expressed by Men","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.06861","title":"BiasLab: A Multilingual Dual-Framing Framework for LLM Bias Measurement, Applied to Workplace and HR Contexts","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2601.10102","title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","created":"2026-01-15","cited_by_count":0,"area":"agents"},{"id":"2601.13749","title":"Pro-AI Bias in Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.04739","title":"Alignment Drift in Multimodal LLMs: A Two-Phase, Longitudinal Evaluation of Harm Across Eight Model Releases","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"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":"2604.27661","title":"Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.16153","title":"An Algebraic Exposition of the Theory of Dyadic Morality","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.16538","title":"LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.23157","title":"Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs","created":"2026-05-22","cited_by_count":0,"area":"mllm"},{"id":"2606.17810","title":"No-Free-Fairness: Fundamental Limits and Trade-offs in Learning Systems","created":"2026-06-16","cited_by_count":0,"area":null},{"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":"2607.25447","title":"CoRenew: A large language model agent-based policy simulation platform for multifamily residential redevelopment","created":"2026-07-28","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}