{"total":146,"rows":[{"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":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126,"area":"agents"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79,"area":null},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60,"area":"agents"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"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":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","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":"2406.14595","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":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31,"area":"agents"},{"id":"2501.11378","title":"Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio","created":"2025-01-20","cited_by_count":31,"area":null},{"id":"2503.10728","title":"DarkBench: Benchmarking Dark Patterns in Large Language Models","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2506.04018","title":"AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents","created":"2025-06-04","cited_by_count":22,"area":"agents"},{"id":"2505.14352","title":"Towards eliciting latent knowledge from LLMs with mechanistic interpretability","created":"2025-05-20","cited_by_count":19,"area":"mechinterp"},{"id":"2601.01685","title":"Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage","created":"2026-01-04","cited_by_count":19,"area":"lr"},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2510.27378","title":"Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity","created":"2025-10-31","cited_by_count":17,"area":"lr"},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"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":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"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":"2405.04325","title":"Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation","created":"2024-05-07","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":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2507.22149","title":"When Truthful Representations Flip Under Deceptive Instructions?","created":"2025-07-29","cited_by_count":10,"area":"mechinterp"},{"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":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2505.13787","title":"Preference Learning with Lie Detectors can Induce Honesty or Evasion","created":"2025-05-20","cited_by_count":9,"area":"alignment"},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","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":"2510.08211","title":"LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions","created":"2025-10-09","cited_by_count":8,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2407.11789","title":"Large Language Models as Misleading Assistants in Conversation","created":"2024-07-16","cited_by_count":7,"area":null},{"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":"2603.16928","title":"Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback","created":"2026-03-14","cited_by_count":7,"area":"lr"},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","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":"2409.13714","title":"TracrBench: Generating Interpretability Testbeds with Large Language Models","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2411.11853","title":"Chat Bankman-Fried: an Exploration of LLM Alignment in Finance","created":"2024-11-01","cited_by_count":5,"area":"alignment"},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2409.16125","title":"Analyzing Probabilistic Methods for Evaluating Agent Capabilities","created":"2024-09-24","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":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2508.05625","title":"How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations","created":"2025-08-07","cited_by_count":4,"area":"mechinterp"},{"id":"2605.27593","title":"Voluntary Collusion with Secret Tools in Competing LLM Agents","created":"2026-05-26","cited_by_count":4,"area":"agents"},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2605.30322","title":"Gram: Assessing sabotage propensities via automated alignment auditing","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.12323","title":"Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"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"},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"id":"2604.09104","title":"Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence","created":"2026-04-10","cited_by_count":3,"area":null},{"id":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.06490","title":"Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2410.00061","title":"Neural Decompiling of Tracr Transformers","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2505.02709","title":"Technical Report: Evaluating Goal Drift in Language Model Agents","created":"2025-05-05","cited_by_count":2,"area":"agents"},{"id":"2506.16150","title":"PRISON: Unmasking the Criminal Potential of Large Language Models","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2510.23245","title":"Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2601.08768","title":"AI as Entertainment","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2601.13709","title":"Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2603.05872","title":"Evolving Deception: When Agents Evolve, Deception Wins","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2604.04561","title":"Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2605.10059","title":"Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.28114","title":"Language model agents show in-group trust bias invisible to standard behavioural audits","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.17478","title":"Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing","created":"2026-06-16","cited_by_count":2,"area":"lr"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2406.19552","title":"Rethinking harmless refusals when fine-tuning foundation models","created":"2024-06-27","cited_by_count":1,"area":"lr"},{"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":"2505.07846","title":"Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models","created":"2025-05-07","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":"2510.04528","title":"Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"id":"2601.10896","title":"DialDefer: A Framework for Detecting and Mitigating LLM Dialogic Deference","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2602.16987","title":"A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agents","created":"2026-02-19","cited_by_count":1,"area":"alignment"},{"id":"2603.07202","title":"Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2604.04157","title":"Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents","created":"2026-04-05","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}