{"total":101,"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":"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":"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":"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":"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":"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":"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":"2506.16702","title":"Large Language Models as Psychological Simulators: A Methodological Guide","created":"2025-06-20","cited_by_count":6,"area":null},{"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":"2510.21977","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":"2505.21451","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":"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":"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":"2511.21218","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":"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":"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":"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":"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":"2609.27690","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":"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":"2603.07329","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":"2605.12530","title":"In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.27395","title":"Informing AI Policy Assessment using Large-Scale Simulation of Interventions","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.27584","title":"Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.29793","title":"Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.08625","title":"The complexities of patient-centred conversational artificial intelligence","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10628","title":"Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.25667","title":"MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.26899","title":"Human diversity fuels collective creativity that large language models cannot simulate or sustain","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.06115","title":"Mind the Gaps: Mixture-of-Minds for Human Simulation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07316","title":"Natural Language Processing Psychometrics","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.09717","title":"How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14692","title":"Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.00565","title":"Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04835","title":"On Epistemic Diversity in Large Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.07353","title":"Human-like moral judgments conceal divergent motive attributions in large language models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.07598","title":"Mapping the Emerging Social Science of Large Language Models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.16454","title":"Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.22934","title":"Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.25066","title":"Understanding Reliability in LLM-based Human Behavior Simulation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.26629","title":"PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.29928","title":"Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33055","title":"Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35302","title":"Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36253","title":"Population Fidelity: Evaluating Population Representativeness in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.03998","title":"Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14912","title":"Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":"100"}