{"total":61,"rows":[{"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":"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":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"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":"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":"2502.19312","title":"FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users","created":"2025-02-26","cited_by_count":15,"area":"alignment"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2507.13490","title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2510.11586","title":"Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2506.09998","title":"Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling","created":"2025-06-11","cited_by_count":7,"area":null},{"id":"2507.17216","title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2506.00052","title":"Using LLMs to Advance the Cognitive Science of Collectives","created":"2025-05-28","cited_by_count":6,"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":"2605.20767","title":"The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study","created":"2026-05-20","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":"2602.06357","title":"LLM-SAA: LLM-persona Generated Distributions for Decision-making","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.08229","title":"InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation","created":"2026-02-09","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":"2604.02319","title":"No Single Best Model for Diversity: Learning a Router for Sample Diversity","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2606.05376","title":"SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.15277","title":"Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models","created":"2026-07-16","cited_by_count":2,"area":"lr"},{"id":"2505.02072","title":"Express Your Doubts -- Probabilistic World Modeling Should not be Based on Token logprobs","created":"2025-05-04","cited_by_count":1,"area":"wm"},{"id":"2510.13884","title":"Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation","created":"2025-10-14","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":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2603.19002","title":"RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation","created":"2026-03-19","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":"2605.31099","title":"KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.09351","title":"In-Context Learning for the Imputation of Public Opinion Data with Large Language Models","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.21939","title":"Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2606.24162","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.25292","title":"Instruction-Tuned Language Models Cannot Sample from Distributions They Can Describe","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.29455","title":"Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates","created":"2026-08-29","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":"2509.08217","title":"Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.09524","title":"DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2512.05982","title":"FlockVote: LLM-Empowered Agent-Based Modeling for Simulating U.S. Presidential Elections","created":"2025-11-27","cited_by_count":0,"area":"agents"},{"id":"2603.13305","title":"Evidence-based Distributional Alignment for Large Language Models","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"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":"2604.06201","title":"Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.29631","title":"Predicting Causal Effects from Natural Language Queries using Structured Representations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.13254","title":"Evaluating Pluralism in LLMs through Latent Perspectives","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.06875","title":"Video2Reaction: Mapping Video to Audience Reaction Distribution in the Wild","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.01458","title":"PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.03044","title":"Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05576","title":"Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.00222","title":"LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","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":"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":"2609.34929","title":"Sample What You Say: Aligning Language Models to Sample the Distributions They State","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.39483","title":"Who Owns That? Evaluating Ownership Intuitions in Large Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05828","title":"Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes","created":"2026-10-05","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},{"id":"2610.20472","title":"ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}