{"total":16,"rows":[{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"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":"2510.15501","title":"DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios","created":"2025-10-17","cited_by_count":19,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2502.13259","title":"HumT DumT: Measuring and controlling human-like language in LLMs","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2510.14318","title":"Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2507.16196","title":"Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2510.01395","title":"Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2506.16150","title":"PRISON: Unmasking the Criminal Potential of Large Language Models","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2603.20907","title":"The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues","created":"2026-03-21","cited_by_count":2,"area":null},{"id":"2604.15607","title":"Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.10990","title":"When Verification Fails: How Compositionally Infeasible Claims Escape Rejection","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.19270","title":"DECOR: Auditing LLM Deception via Information Manipulation Theory","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}