{"total":163,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2411.11581","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","created":"2024-11-18","cited_by_count":132,"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":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81,"area":null},{"id":"2407.03103","title":"Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory","created":"2024-07-03","cited_by_count":60,"area":null},{"id":"2405.11591","title":"Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation","created":"2024-05-19","cited_by_count":58,"area":null},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2407.13943","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","created":"2024-07-18","cited_by_count":45,"area":null},{"id":"2412.17767","title":"ResearchTown: Simulator of Human Research Community","created":"2024-12-23","cited_by_count":37,"area":null},{"id":"2311.09730","title":"Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs","created":"2023-11-16","cited_by_count":36,"area":null},{"id":"2402.13610","title":"Data-driven Discovery with Large Generative Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2408.16629","title":"LLMs generate structurally realistic social networks but overestimate political homophily","created":"2024-08-29","cited_by_count":33,"area":null},{"id":"2409.19430","title":"'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants","created":"2024-09-28","cited_by_count":28,"area":null},{"id":"2503.01829","title":"Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2406.12203","title":"InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context","created":"2024-06-18","cited_by_count":26,"area":null},{"id":"2502.09082","title":"CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation","created":"2025-02-13","cited_by_count":26,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2502.07077","title":"Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models","created":"2025-02-10","cited_by_count":25,"area":null},{"id":"2508.01674","title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","created":"2025-08-03","cited_by_count":22,"area":null},{"id":"2403.06769","title":"Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation","created":"2024-03-11","cited_by_count":21,"area":null},{"id":"2408.04203","title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2504.09689","title":"EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety","created":"2025-04-13","cited_by_count":21,"area":null},{"id":"2406.17260","title":"Mitigating Hallucination in Fictional Character Role-Play","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2407.04503","title":"When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2502.21017","title":"PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues","created":"2025-02-28","cited_by_count":17,"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":"2506.23046","title":"SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions","created":"2025-06-29","cited_by_count":16,"area":null},{"id":"2404.04204","title":"Social Skill Training with Large Language Models","created":"2024-04-05","cited_by_count":15,"area":null},{"id":"2511.22173","title":"RefineBench: Evaluating Refinement Capability of Language Models via Checklists","created":"2025-11-27","cited_by_count":15,"area":null},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2402.12556","title":"IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2403.06591","title":"Academically intelligent LLMs are not necessarily socially intelligent","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2503.02016","title":"Mind the (Belief) Gap: Group Identity in the World of LLMs","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2504.21582","title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","created":"2025-04-30","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":"2403.14659","title":"Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future","created":"2024-02-28","cited_by_count":11,"area":null},{"id":"2406.13993","title":"Exploring Changes in Nation Perception with Nationality-Assigned Personas in LLMs","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11,"area":null},{"id":"2507.20352","title":"RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing","created":"2025-07-27","cited_by_count":10,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2504.17993","title":"Improving Language Model Personas via Rationalization with Psychological Scaffolds","created":"2025-04-25","cited_by_count":9,"area":null},{"id":"2507.10599","title":"Emergence of Hierarchical Emotion Organization in Large Language Models","created":"2025-07-12","cited_by_count":9,"area":null},{"id":"2409.07641","title":"SimulBench: Evaluating Language Models with Creative Simulation Tasks","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2507.08892","title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2605.18890","title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","created":"2026-05-17","cited_by_count":8,"area":null},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2407.12393","title":"PersLLM: A Personified Training Approach for Large Language Models","created":"2024-07-17","cited_by_count":6,"area":null},{"id":"2510.25744","title":"Completion $\\neq$ Collaboration: Scaling Collaborative Effort with Agents","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2406.16152","title":"Towards Region-aware Bias Evaluation Metrics","created":"2024-06-23","cited_by_count":5,"area":null},{"id":"2410.04054","title":"Large Language Models can Achieve Social Balance","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2503.23514","title":"If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2505.12814","title":"PsyMem: Fine-grained psychological alignment and Explicit Memory Control for Advanced Role-Playing LLMs","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2512.07890","title":"CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2408.09330","title":"Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2506.14159","title":"StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2511.08565","title":"Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models","created":"2025-11-11","cited_by_count":4,"area":null},{"id":"2604.18982","title":"SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2605.09228","title":"ProactBench: Beyond What The User Asked For","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2409.09135","title":"Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2507.08491","title":"A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2509.11206","title":"Evalet: Evaluating Large Language Models through Functional Fragmentation","created":"2025-09-14","cited_by_count":3,"area":null},{"id":"2510.09087","title":"The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2512.11844","title":"Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2601.01530","title":"EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World","created":"2026-01-04","cited_by_count":3,"area":null},{"id":"2604.05523","title":"Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.09826","title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2608.05583","title":"The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2402.09984","title":"Symmetry-Breaking Augmentations for Ad Hoc Teamwork","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2412.07019","title":"Assessing the Impact of Conspiracy Theories Using Large Language Models","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2503.16545","title":"EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2505.19558","title":"PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.00741","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.02461","title":"XToM: Exploring the Multilingual Theory of Mind for Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.13783","title":"Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents","created":"2025-06-10","cited_by_count":2,"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":"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":"2510.21180","title":"Social Simulations with Large Language Model Risk Utopian Illusion","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2603.10035","title":"TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2604.13846","title":"Beyond Static Personas: Situational Personality Steering for Large Language Models","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2604.20443","title":"DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2604.25840","title":"PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators","created":"2026-04-28","cited_by_count":2,"area":null},{"id":"2605.16575","title":"Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2608.05170","title":"DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2410.04751","title":"Intriguing Properties of Large Language and Vision Models","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2411.07042","title":"How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response","created":"2024-11-11","cited_by_count":1,"area":null}],"next_cursor":"100"}