{"total":34,"rows":[{"id":"2510.23191","title":"The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models","created":"2025-10-27","cited_by_count":13,"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":"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":"2507.04491","title":"A validity-guided workflow for robust large language model research in psychology","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2604.27405","title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2605.30803","title":"PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2606.09843","title":"An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models","created":"2026-04-24","cited_by_count":4,"area":null},{"id":"2506.22493","title":"A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2507.05890","title":"Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2510.11734","title":"Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2601.12727","title":"AI-exhibited Personality Traits Can Shape Human Self-concept through Conversations","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2606.00860","title":"GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing","created":"2026-05-30","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":"2511.00527","title":"A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2602.17262","title":"Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2604.17707","title":"Before You Interpret the Profile: Validity Scaling for LLM Metacognitive Self-Report","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2606.20205","title":"Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2510.03384","title":"Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2511.19872","title":"Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.08646","title":"QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2603.18019","title":"BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2608.10703","title":"Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.16196","title":"Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2608.27463","title":"Rating the Raters: Rasch Measurement Theory for LLM Evaluation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2609.02899","title":"Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2509.04646","title":"Towards Personalized Explanations for Health Simulations: A Mixed-Methods Framework for Stakeholder-Centric Summarization","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2511.01840","title":"A Detailed Study on LLM Biases Concerning Corporate Social Responsibility and Green Supply Chains","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.03546","title":"Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2603.23506","title":"Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2606.16127","title":"AuAu: A Benchmark for Auditing Authoritarian Alignment in Large Language Models","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.26853","title":"From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.31184","title":"Accounting for Bias Enables Sustainable LLM Evaluation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.02877","title":"Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18248","title":"Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}