{"total":144,"rows":[{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"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":"2506.07962","title":"Correlated Errors in Large Language Models","created":"2025-06-09","cited_by_count":45,"area":null},{"id":"2507.16076","title":"The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models","created":"2025-07-21","cited_by_count":42,"area":null},{"id":"2509.05830","title":"Finetuning LLMs for Human Behavior Prediction in Social Science Experiments","created":"2025-09-06","cited_by_count":39,"area":null},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34,"area":null},{"id":"2502.20897","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","created":"2025-02-28","cited_by_count":33,"area":null},{"id":"2405.10632","title":"Towards interactive evaluations for interaction harms in human-AI systems","created":"2024-05-17","cited_by_count":29,"area":null},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"area":"alignment"},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2505.15229","title":"Multilingual Prompting for Improving LLM Generation Diversity","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2410.11005","title":"Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","created":"2024-10-14","cited_by_count":22,"area":"lr"},{"id":"2502.11995","title":"Presumed Cultural Identity: How Names Shape LLM Responses","created":"2025-02-17","cited_by_count":21,"area":null},{"id":"2510.11408","title":"Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification","created":"2025-10-13","cited_by_count":18,"area":null},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2511.07338","title":"DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2509.01418","title":"On the Alignment of Large Language Models with Global Human Opinion","created":"2025-09-01","cited_by_count":13,"area":"alignment"},{"id":"2505.18596","title":"Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2506.16697","title":"From Prompts to Constructs: A Dual-Validity Framework for Large Language Model Research in Psychology","created":"2025-06-20","cited_by_count":9,"area":null},{"id":"2502.13780","title":"Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2510.06105","title":"Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2510.11035","title":"SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents","created":"2025-10-13","cited_by_count":8,"area":"agents"},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2506.14652","title":"Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"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":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2506.16702","title":"Large Language Models as Psychological Simulators: A Methodological Guide","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2508.11416","title":"AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Manager","created":"2025-08-15","cited_by_count":6,"area":"lr"},{"id":"2409.09045","title":"United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections","created":"2024-08-29","cited_by_count":5,"area":null},{"id":"2510.14205","title":"DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans","created":"2025-10-16","cited_by_count":5,"area":"agents"},{"id":"2510.21977","title":"Distribution Shift Alignment Helps LLMs Simulate Survey Response Distributions","created":"2025-10-24","cited_by_count":5,"area":null},{"id":"2511.21722","title":"German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2601.16355","title":"Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans","created":"2026-01-22","cited_by_count":5,"area":null},{"id":"2505.10309","title":"A large-scale evaluation of commonsense knowledge in humans and large language models","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2505.17390","title":"Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Prompting","created":"2025-05-23","cited_by_count":4,"area":"synth"},{"id":"2505.21451","title":"Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2505.23827","title":"ValueSim: Generating Backstories to Model Individual Value Systems","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2509.03736","title":"Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulation","created":"2025-09-03","cited_by_count":4,"area":"agents"},{"id":"2604.06663","title":"Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.10659","title":"When Can Digital Personas Reliably Approximate Human Survey Findings?","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2506.16163","title":"Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.00088","title":"How large language models judge and influence human cooperation","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2510.13902","title":"Investigating Political and Demographic Associations in Large Language Models Through Moral Foundations Theory","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2604.11721","title":"Evaluating Cooperation in LLM Social Groups through Elected Leadership","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2606.28963","title":"Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data","created":"2026-06-27","cited_by_count":3,"area":null},{"id":"2505.18351","title":"Persona Alchemy: Designing, Evaluating, and Implementing Psychologically-Grounded LLM Agents for Diverse Stakeholder Representation","created":"2025-05-23","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":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2510.03310","title":"Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.16829","title":"Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation","created":"2025-10-19","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":"2511.21218","title":"Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.00685","title":"HumanStudy-Bench: Towards AI Agent Design for Participant Simulation","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2603.12471","title":"Marked Pedagogies: Examining Linguistic Biases in Personalized Automated Writing Feedback","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2603.16142","title":"Parametric Social Identity Injection and Diversification in Public Opinion Simulation","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.22749","title":"Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.02624","title":"Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.16303","title":"From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes","created":"2026-04-24","cited_by_count":2,"area":"agents"},{"id":"2609.02526","title":"When Persona Attributes Improve Population Alignment in Large Language Models","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2504.01951","title":"The LLM Wears Prada: Analysing Gender Bias and Stereotypes through Online Shopping Data","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2508.08719","title":"IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2603.21404","title":"Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2603.29890","title":"Interview-Informed Generative Agents for Product Discovery: A Validation Study","created":"2026-03-10","cited_by_count":1,"area":"agents"},{"id":"2604.02458","title":"Statistical realism is not evidence that LLMs can estimate treatment effects in social science experiments","created":"2026-04-02","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":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.10428","title":"Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.18310","title":"Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.24782","title":"Personalization, Personas, and Forecasting in Value Alignment","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2608.19621","title":"Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"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":"2609.04738","title":"Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.07987","title":"When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.25760","title":"The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance","created":"2026-09-22","cited_by_count":1,"area":"alignment"},{"id":"2609.27690","title":"Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2504.06160","title":"Navigating the Rabbit Hole: Emergent Biases in LLM-Generated Attack Narratives Targeting Mental Health Groups","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2509.25283","title":"Effectiveness of Large Language Models in Simulating Regional Psychological Structures: An Empirical Examination of Personality and Subjective Well-being","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2511.23041","title":"Social Perceptions of English Spelling Variation on Twitter: A Comparative Analysis of Human and LLM Responses","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.12444","title":"Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.23889","title":"How Large Language Models Systematically Misrepresent American Climate Opinions","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2601.03396","title":"Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.15319","title":"Large Language Models as Simulative Agents for Neurodivergent Adult Psychometric Profiles","created":"2026-01-16","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":"2601.22288","title":"PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design Research","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2602.02878","title":"Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.02420","title":"Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.07329","title":"The Third Ambition: Artificial Intelligence and the Science of Human Behavior","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.15329","title":"Evaluating LLMs as Human Surrogates in Controlled Experiments","created":"2026-03-08","cited_by_count":0,"area":"synth"},{"id":"2605.12530","title":"In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":"100"}