{"total":28,"rows":[{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"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":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"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":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2502.16797","title":"Forecasting Rare Language Model Behaviors","created":"2025-02-24","cited_by_count":19,"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":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2412.08653","title":"What AI evaluations for preventing catastrophic risks can and cannot do","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"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":"2606.09809","title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2602.16984","title":"Fundamental Limits of Black-Box Safety Evaluation: Information-Theoretic and Computational Barriers from Latent Context Conditioning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2607.20436","title":"Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2510.12117","title":"Locket: Robust Feature-Locking Technique for Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2606.06286","title":"LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2608.29458","title":"Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2608.29461","title":"A Causal Model for Locating and Unlocking Sandbagging in Model Organisms","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2603.14672","title":"Seamless Deception: Larger Language Models Are Better Knowledge Concealers","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.21638","title":"Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.03478","title":"Demonstrating Generalization Failures via Mixtures of Conditional Policies","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2609.32530","title":"Activation Flow: Manufacturing Activations for Steering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14519","title":"Query-Adaptive Neuron Steering for LLMs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}