{"total":188,"rows":[{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168,"area":"agents"},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"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":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104,"area":"lr"},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2402.19379","title":"Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy","created":"2024-02-29","cited_by_count":67,"area":null},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2401.02843","title":"Thousands of AI Authors on the Future of AI","created":"2024-01-05","cited_by_count":48,"area":null},{"id":"2405.08007","title":"People cannot distinguish GPT-4 from a human in a Turing test","created":"2024-05-09","cited_by_count":48,"area":null},{"id":"2503.23674","title":"Large Language Models Pass the Turing Test","created":"2025-03-31","cited_by_count":48,"area":null},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2403.01251","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","created":"2024-03-02","cited_by_count":37,"area":"safety"},{"id":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2312.10029","title":"Challenges with unsupervised LLM knowledge discovery","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"id":"2309.01933","title":"Provably safe systems: the only path to controllable AGI","created":"2023-09-05","cited_by_count":29,"area":null},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2412.07951","title":"From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agents","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2310.13014","title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","created":"2023-10-17","cited_by_count":24,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2403.04471","title":"The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists","created":"2024-03-07","cited_by_count":22,"area":null},{"id":"2402.07862","title":"AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"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":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","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":"2405.14808","title":"Implicit Personalization in Language Models: A Systematic Study","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2406.00380","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","created":"2024-06-01","cited_by_count":18,"area":null},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17,"area":"alignment"},{"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":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"area":"agents"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2501.05382","title":"Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2410.13915","title":"A Simulation System Towards Solving Societal-Scale Manipulation","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2506.07388","title":"Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents","created":"2025-06-09","cited_by_count":12,"area":"agents"},{"id":"2406.18346","title":"AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations","created":"2024-06-26","cited_by_count":11,"area":"alignment"},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2409.07085","title":"Understanding Knowledge Drift in LLMs through Misinformation","created":"2024-09-11","cited_by_count":10,"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":"2404.13060","title":"The Necessity of AI Audit Standards Boards","created":"2024-04-11","cited_by_count":9,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2506.08572","title":"The Geometries of Truth Are Orthogonal Across Tasks","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2509.23023","title":"Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia","created":"2025-09-27","cited_by_count":9,"area":null},{"id":"2602.01425","title":"One Probe Won't Catch Them All: Towards Targeted Deception Detection","created":"2026-02-01","cited_by_count":9,"area":"mechinterp"},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2502.20426","title":"Among Them: A game-based framework for assessing persuasion capabilities of LLMs","created":"2025-02-27","cited_by_count":8,"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":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2405.11612","title":"Sociotechnical Implications of Generative Artificial Intelligence for Information Access","created":"2024-05-19","cited_by_count":6,"area":null},{"id":"2506.18852","title":"Mechanistic Interpretability Needs Philosophy","created":"2025-06-23","cited_by_count":6,"area":"mechinterp"},{"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":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2502.04230","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2504.13707","title":"OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation","created":"2025-04-18","cited_by_count":5,"area":"agents"},{"id":"2508.06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","created":"2025-08-08","cited_by_count":5,"area":"lr"},{"id":"2606.16475","title":"AI systems out-persuade expert humans","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2406.06874","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2407.18712","title":"Cluster-norm for Unsupervised Probing of Knowledge","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2412.17797","title":"Observation Interference in Partially Observable Assistance Games","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2601.00360","title":"Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2604.13386","title":"Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling","created":"2026-04-15","cited_by_count":4,"area":"alignment"},{"id":"2605.00073","title":"AgentReputation: A Decentralized Agentic AI Reputation Framework","created":"2026-04-30","cited_by_count":4,"area":"agents"},{"id":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2311.08487","title":"Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective","created":"2023-11-14","cited_by_count":3,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2501.15054","title":"Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2505.17760","title":"But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"}],"next_cursor":"100"}