{"total":24,"rows":[{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2407.01294","title":"A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms","created":"2024-07-01","cited_by_count":19,"area":null},{"id":"2402.01708","title":"Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators","created":"2024-01-25","cited_by_count":18,"area":null},{"id":"2310.14455","title":"An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2503.04739","title":"A Framework for Responsible AI Systems: Building Societal Trust through Domain Definition, Trustworthy AI Design, Auditability, Accountability, and Governance","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2402.08062","title":"Avoiding Catastrophe in Online Learning by Asking for Help","created":"2024-02-12","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":"2607.02197","title":"Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond","created":"2026-07-02","cited_by_count":4,"area":null},{"id":"2410.03092","title":"Strategic Insights from Simulation Gaming of AI Race Dynamics","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2508.08804","title":"TechOps: Technical Documentation Templates for the AI Act","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2608.23875","title":"AI Finds A Way","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2503.07341","title":"The Economics of p(doom): Scenarios of Existential Risk and Economic Growth in the Age of Transformative AI","created":"2025-03-10","cited_by_count":2,"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":"2307.14283","title":"General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2404.11476","title":"Taxonomy to Regulation: A (Geo)Political Taxonomy for AI Risks and Regulatory Measures in the EU AI Act","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","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":"2507.09369","title":"A Taxonomy of Omnicidal Futures Involving Artificial Intelligence","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2511.19115","title":"AI Consciousness and Existential Risk","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.20805","title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.26494","title":"Culturally Situated AI Safety for Youth: Saudi Arabian Perspectives of Youth, Parents and Teachers","created":"2026-04-29","cited_by_count":0,"area":null}],"next_cursor":null}