{"total":112,"rows":[{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179,"area":null},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169,"area":null},{"id":"2402.16786","title":"Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models","created":"2024-02-26","cited_by_count":162,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85,"area":null},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82,"area":"agents"},{"id":"2303.01248","title":"Can ChatGPT Assess Human Personalities? A General Evaluation Framework","created":"2023-03-01","cited_by_count":70,"area":null},{"id":"2406.14703","title":"Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics","created":"2024-06-20","cited_by_count":59,"area":null},{"id":"2410.18417","title":"Large Language Models Reflect the Ideology of their Creators","created":"2024-10-24","cited_by_count":57,"area":null},{"id":"2308.03656","title":"Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench","created":"2023-08-07","cited_by_count":54,"area":null},{"id":"2312.15198","title":"Do LLM Agents Exhibit Social Behavior?","created":"2023-12-23","cited_by_count":53,"area":"agents"},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50,"area":null},{"id":"2406.04428","title":"MoralBench: Moral Evaluation of LLMs","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2307.07870","title":"Large Language Models as Superpositions of Cultural Perspectives","created":"2023-07-15","cited_by_count":49,"area":null},{"id":"2311.09718","title":"You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments","created":"2023-11-16","cited_by_count":48,"area":null},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45,"area":"lr"},{"id":"2309.08163","title":"Self-Assessment Tests are Unreliable Measures of LLM Personality","created":"2023-09-15","cited_by_count":39,"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":"2312.10075","title":"Assessing LLMs for Moral Value Pluralism","created":"2023-12-08","cited_by_count":34,"area":null},{"id":"2312.17476","title":"Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters","created":"2023-12-29","cited_by_count":32,"area":null},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2402.10659","title":"Network Formation and Dynamics Among Multi-LLMs","created":"2024-02-16","cited_by_count":29,"area":"wm"},{"id":"2310.01386","title":"Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench","created":"2023-10-02","cited_by_count":28,"area":null},{"id":"2502.05248","title":"Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"area":null},{"id":"2303.13988","title":"Machine Psychology","created":"2023-03-24","cited_by_count":22,"area":null},{"id":"2310.02168","title":"Editing Personality for Large Language Models","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","cited_by_count":21,"area":null},{"id":"2401.07115","title":"Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models","created":"2024-01-13","cited_by_count":20,"area":"agents"},{"id":"2406.04214","title":"ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2505.01015","title":"Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items","created":"2025-05-02","cited_by_count":18,"area":null},{"id":"2303.06074","title":"Susceptibility to Influence of Large Language Models","created":"2023-03-10","cited_by_count":17,"area":null},{"id":"2401.01519","title":"Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review","created":"2024-01-03","cited_by_count":17,"area":null},{"id":"2305.19926","title":"Revisiting the Reliability of Psychological Scales on Large Language Models","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2306.04308","title":"Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality","created":"2023-06-07","cited_by_count":16,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2410.17632","title":"LMLPA: Language Model Linguistic Personality Assessment","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2402.14846","title":"Stick to your Role! Stability of Personal Values Expressed in Large Language Models","created":"2024-02-19","cited_by_count":14,"area":null},{"id":"2407.12878","title":"Do LLMs have Consistent Values?","created":"2024-07-16","cited_by_count":14,"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":"2310.04450","title":"Investigating Large Language Models' Perception of Emotion Using Appraisal Theory","created":"2023-10-03","cited_by_count":12,"area":null},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2406.17624","title":"Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models","created":"2024-06-25","cited_by_count":11,"area":null},{"id":"2310.17857","title":"From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2402.14805","title":"Identifying Multiple Personalities in Large Language Models with External Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2505.00049","title":"Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications","created":"2025-04-30","cited_by_count":10,"area":"agents"},{"id":"2503.04735","title":"How Personality Traits Shape LLM Risk-Taking Behaviour","created":"2025-02-03","cited_by_count":9,"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":"2310.10679","title":"Large language models can replicate cross-cultural differences in personality","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2402.14679","title":"Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality","created":"2024-02-22","cited_by_count":8,"area":null},{"id":"2409.15890","title":"HLB: Benchmarking LLMs' Humanlikeness in Language Use","created":"2024-09-24","cited_by_count":8,"area":null},{"id":"2506.12078","title":"Modeling Earth-Scale Human-Like Societies with One Billion Agents","created":"2025-06-07","cited_by_count":8,"area":"agents"},{"id":"2506.19352","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","created":"2025-06-24","cited_by_count":8,"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":"2507.13490","title":"Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2310.16582","title":"UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2310.11227","title":"RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2406.12216","title":"Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptions","created":"2024-06-18","cited_by_count":5,"area":"agents"},{"id":"2406.19238","title":"Revealing Fine-Grained Values and Opinions in Large Language Models","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2504.12313","title":"Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2505.12792","title":"EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2505.09820","title":"Adversarial Attack on Large Language Models using Exponentiated Gradient Descent","created":"2025-05-14","cited_by_count":4,"area":"safety"},{"id":"2507.03123","title":"Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations","created":"2025-07-03","cited_by_count":4,"area":"mllm"},{"id":"2602.08567","title":"ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":4,"area":"agents"},{"id":"2409.10245","title":"From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs","created":"2024-09-16","cited_by_count":3,"area":"mechinterp"},{"id":"2409.15324","title":"Cognitive phantoms in LLMs through the lens of latent variables","created":"2024-09-06","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":"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":"2406.04583","title":"Extroversion or Introversion? Controlling The Personality of Your Large Language Models","created":"2024-06-07","cited_by_count":2,"area":"alignment"},{"id":"2408.07377","title":"Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics","created":"2024-08-14","cited_by_count":2,"area":null},{"id":"2506.20993","title":"SAC: A Framework for Measuring and Inducing Personality Traits in LLMs with Dynamic Intensity Control","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2508.14853","title":"Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent","created":"2025-08-20","cited_by_count":2,"area":"alignment"},{"id":"2509.10078","title":"Human Psychometric Questionnaires Mischaracterize LLM Behavior","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2510.07175","title":"Quantifying Data Contamination in Psychometric Evaluations of LLMs","created":"2025-10-08","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":"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":"2605.29791","title":"ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2304.07830","title":"The language of sounds unheard: Exploring musical timbre semantics of large language models","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2402.17411","title":"Consistency Matters: Explore LLMs Consistency From a Black-Box Perspective","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2404.00267","title":"Secret Keepers: The Impact of LLMs on Linguistic Markers of Personal Traits","created":"2024-03-30","cited_by_count":1,"area":null},{"id":"2408.04671","title":"Prompt and Prejudice","created":"2024-08-07","cited_by_count":1,"area":"mllm"},{"id":"2410.08545","title":"Humanity in AI: Detecting the Personality of Large Language Models","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2411.10473","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2504.06868","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2508.00742","title":"Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents","created":"2025-08-01","cited_by_count":1,"area":"agents"},{"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":"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":"2608.23411","title":"STONIC: A Layered Measurement Contract for LLM Value Profiling","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2308.00521","title":"SurveyLM: A platform to explore emerging value perspectives in augmented language models' behaviors","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2405.07495","title":"MacBehaviour: An R package for behavioural experimentation on large language models","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2411.05040","title":"Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs","created":"2024-11-06","cited_by_count":0,"area":null}],"next_cursor":"100"}