{"total":98,"rows":[{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"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":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"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":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97,"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":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"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":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"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":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22,"area":null},{"id":"2502.07663","title":"Human Decision-making is Susceptible to AI-driven Manipulation","created":"2025-02-11","cited_by_count":19,"area":null},{"id":"2403.18152","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","created":"2024-03-26","cited_by_count":18,"area":null},{"id":"2409.09467","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","created":"2024-09-14","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":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"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":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2307.10569","title":"Deceptive Alignment Monitoring","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2406.01364","title":"BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2406.06435","title":"Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain","created":"2024-06-10","cited_by_count":14,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"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":"2411.11731","title":"Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment","created":"2024-11-18","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":"2603.07368","title":"Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness","created":"2026-03-07","cited_by_count":10,"area":null},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","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":"2307.00787","title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios","created":"2023-07-03","cited_by_count":8,"area":null},{"id":"2409.20303","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","created":"2024-09-30","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":"2309.06364","title":"Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2407.19760","title":"Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2402.11811","title":"FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"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":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2603.25326","title":"Evaluating Language Models for Harmful Manipulation","created":"2026-03-26","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":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2305.08290","title":"SWAN: A Generic Framework for Auditing Textual Conversational Systems","created":"2023-05-15","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":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2406.04752","title":"CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2410.18991","title":"TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2509.12190","title":"Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2510.21460","title":"Risk Management for Mitigating Benchmark Failure Modes: BenchRisk","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2304.14553","title":"Appropriateness is all you need!","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2312.03721","title":"Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2406.03428","title":"HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits","created":"2024-06-05","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":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2405.07282","title":"Branching Narratives: Character Decision Points Detection","created":"2024-05-12","cited_by_count":1,"area":null},{"id":"2408.14507","title":"Prompt-Matcher: Leveraging Large Models to Reduce Uncertainty in Schema Matching Results","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2411.08884","title":"Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2501.09025","title":"Cyber Shadows: Neutralizing Security Threats with AI and Targeted Policy Measures","created":"2025-01-03","cited_by_count":1,"area":null},{"id":"2504.06868","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.11365","title":"Phare: A Safety Probe for Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2506.21961","title":"PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2602.20813","title":"Pressure Reveals Character: Behavioural Alignment Evaluation at Depth","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2605.13825","title":"History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.18239","title":"SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2609.07731","title":"The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2402.09734","title":"Agents Need Not Know Their Purpose","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2408.12250","title":"Can Artificial Intelligence Embody Moral Values?","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2506.05171","title":"Towards provable probabilistic safety for scalable embodied AI systems","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2511.20689","title":"Morality in AI. A plea to embed morality in LLM architectures and frameworks","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2601.09765","title":"AI Survival Stories: a Taxonomic Analysis of AI Existential Risk","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.15252","title":"Decision Making under Imperfect Recall: Algorithms and Benchmarks","created":"2026-02-16","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":"2603.08024","title":"ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.13250","title":"The Missing Red Line: How Commercial Pressure Erodes AI Safety Boundaries","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.12500","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14593","title":"Mechanistic Decoding of Cognitive Constructs in Large Language Models","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.14744","title":"Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems","created":"2026-05-14","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":"2609.04444","title":"HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07675","title":"Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.08670","title":"Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment","created":"2026-10-06","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},{"id":"2610.15179","title":"UDHRBench: Benchmarking Human Rights in Large Language Models","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16043","title":"Beyond the greenwash: do LLMs' ecologically sound decisions hold up under pressure?","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}