{"total":25,"rows":[{"id":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"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":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"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":"2507.15886","title":"Combining Cost-Constrained Runtime Monitors for AI Safety","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2603.03992","title":"Measuring AI R&D Automation","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2604.22082","title":"Removing Sandbagging in LLMs by Training with Weak Supervision","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"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":"2412.15433","title":"Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2602.17045","title":"Large Language Models Persuade Without Planning Theory of Mind","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2605.29729","title":"Realistic honeypot evaluations for scheming propensity","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.04413","title":"(Mis)generalization of Helpful-only Fine-tuning","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2604.13301","title":"Honeypot Protocol","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.10456","title":"The Distributed Detectability Band Against Marginal-Preserving Attacks","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.04222","title":"Unsupervised Features Mining via Activation Geometry","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.14796","title":"AI Persuasion as a Threat to Human Control","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.09371","title":"The Confidence Game: Strategic Miscalibration in Human-AI Delegation","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}