{"total":32,"rows":[{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2501.09674","title":"Authenticated Delegation and Authorized AI Agents","created":"2025-01-16","cited_by_count":65,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"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":"2410.13204","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","created":"2024-10-17","cited_by_count":11,"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":"2412.01946","title":"The Reality of AI and Biorisk","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2502.15873","title":"Practical Principles for AI Cost and Compute Accounting","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2412.02730","title":"Shaping AI's Impact on Billions of Lives","created":"2024-12-03","cited_by_count":1,"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":"2507.10585","title":"A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2508.06411","title":"Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.22742","title":"Societal Capacity Assessment Framework: Measuring Resilience to Inform Advanced AI Risk Management","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2603.01630","title":"SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2601.18127","title":"The Limits of AI Data Transparency Policy: Three Disclosure Fallacies","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.23183","title":"Designing escalation criteria for international AI incident response: criteria, triggers, and thresholds","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.24538","title":"Is Decentralized AI Governable? From Regulative Policy to Constitutive Protocol","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.18532","title":"AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.02774","title":"Privacy-Preserving AI Verification via Minimal Information Disclosure","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.19216","title":"Bounded Sovereignty and the Control Tax: Pricing AI Oversight When the Deployer Does Not Own the Model","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.00309","title":"Workload Identification with Physical Side Channels for AI Governance","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.10105","title":"Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.39037","title":"Hard-Gate Candidacy in a Deployed Validator Suite","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02928","title":"Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07476","title":"Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}