{"total":57,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66,"area":null},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2402.17649","title":"Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs","created":"2024-02-27","cited_by_count":55,"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":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51,"area":null},{"id":"2410.13341","title":"Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data","created":"2024-10-17","cited_by_count":51,"area":null},{"id":"2408.06929","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","created":"2024-08-13","cited_by_count":37,"area":null},{"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":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"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":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2407.08563","title":"Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2507.23009","title":"Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead","created":"2025-07-30","cited_by_count":7,"area":null},{"id":"2406.17972","title":"LABOR-LLM: Language-Based Occupational Representations with Large Language Models","created":"2024-06-25","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":"2607.26348","title":"When Synthetic Users Fail: A Cross-Domain Benchmark of LLM-Simulated Human Survey Responses","created":"2026-07-28","cited_by_count":5,"area":null},{"id":"2502.02444","title":"Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models","created":"2025-02-04","cited_by_count":4,"area":null},{"id":"2511.02458","title":"Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas","created":"2025-11-04","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":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2511.03070","title":"Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2504.06324","title":"From Stability to Inconsistency: A Study of Moral Preferences in LLMs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.14997","title":"Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.05220","title":"QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2606.04592","title":"Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2505.12470","title":"NeuroGen: Neural Network Parameter Generation via Large Language Models","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.23743","title":"Positional Bias in Binary Question Answering: How Uncertainty Shapes Model Preferences","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.11534","title":"Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2512.21080","title":"LLM Personas as a Substitute for Field Experiments in Method Benchmarking","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2603.20229","title":"Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issues","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.01846","title":"Do Large Language Models Plan Answer Positions? Position Bias in Multiple-Choice Question Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2607.05552","title":"The yes-no bias of large language models reflects answer order and wording, not shifts in moral judgment","created":"2026-07-06","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":"2512.23889","title":"How Large Language Models Systematically Misrepresent American Climate Opinions","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2604.02527","title":"Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.06820","title":"What Does a Sharing Question Add? Auditing LLM Survey Scores for Misinformation","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.12147","title":"PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior","created":"2026-05-12","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":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.02368","title":"Beyond Cultural Persona Bias: Response Geometry as a Measure for Language Models and People","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","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":"2608.18768","title":"Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22582","title":"Hybrid Panels: Toward Human-AI Collaboration in Survey Research","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.28615","title":"Distributional Validity of a Korean Synthetic Persona Panel: Evidence From the Korea Media Panel Survey","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.18384","title":"GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25010","title":"Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.32758","title":"How Far Do Persona Effects Generalize in Language Models?","created":"2026-09-26","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":null}