{"total":68,"rows":[{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79,"area":null},{"id":"2410.16107","title":"Do LLMs write like humans? Variation in grammatical and rhetorical styles","created":"2024-10-21","cited_by_count":62,"area":null},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2401.05302","title":"Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?","created":"2024-01-10","cited_by_count":22,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"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":"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":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2411.02432","title":"Can LLMs make trade-offs involving stipulated pain and pleasure states?","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13,"area":null},{"id":"2410.10398","title":"Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"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":"2409.03843","title":"Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2509.20393","title":"The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2510.03399","title":"Know Thyself? On the Incapability and Implications of AI Self-Recognition","created":"2025-10-03","cited_by_count":8,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2508.19505","title":"Caught in the Act: a mechanistic approach to detecting deception","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2405.12999","title":"An Assessment of Model-On-Model Deception","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2508.11779","title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","created":"2025-08-15","cited_by_count":5,"area":null},{"id":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2603.16900","title":"Social physics in the age of artificial intelligence","created":"2026-03-04","cited_by_count":5,"area":null},{"id":"2606.16475","title":"AI systems out-persuade expert humans","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2504.08016","title":"Emergence of psychopathological computations in large language models","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2410.15311","title":"Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2411.15243","title":"Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2506.16163","title":"Large Language Models are Near-Optimal Decision-Makers with a Non-Human Learning Behavior","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2510.06975","title":"VelLMes: A high-interaction AI-based deception framework","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2403.09676","title":"Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models","created":"2024-02-07","cited_by_count":2,"area":null},{"id":"2410.00061","title":"Neural Decompiling of Tracr Transformers","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2,"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":"2507.08027","title":"\"Amazing, They All Lean Left\" -- Analyzing the Political Temperaments of Current LLMs","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2507.21839","title":"Against racing to AGI: Cooperation, deterrence, and catastrophic risks","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2603.26539","title":"How Open Must Language Models be to Enable Reliable Scientific Inference?","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2308.16364","title":"Strengthening the EU AI Act: Defining Key Terms on AI Manipulation","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2504.00012","title":"I'm Sorry Dave: How the old world of personnel security can inform the new world of AI insider risk","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2505.09807","title":"Exploring the generalization of LLM truth directions on conversational formats","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2601.01584","title":"Steerability of Instrumental-Convergence Tendencies in LLMs","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2606.13310","title":"RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2609.04166","title":"From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2403.14706","title":"Safeguarding Marketing Research: The Generation, Identification, and Mitigation of AI-Fabricated Disinformation","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2407.16994","title":"A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2410.01675","title":"Linguistic traces of stochastic empathy in language models","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2410.14353","title":"Assistive AI for Augmenting Human Decision-making","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2502.13499","title":"Deception at Scale: Deceptive Designs in 1K LLM-Generated Ecommerce Components","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2504.02304","title":"Measurement of LLM's Philosophies of Human Nature","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2510.22219","title":"Estimating the Error of Large Language Models at Pairwise Text Comparison","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2603.06816","title":"\"Dark Triad\" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.10003","title":"Probing the Limits of the Lie Detector Approach to LLM Deception","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.06327","title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08721","title":"Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.01006","title":"Understanding Large Language Models","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.39807","title":"Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}