{"total":20,"rows":[{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"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":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"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":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2404.02675","title":"Responsible Reporting for Frontier AI Development","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"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":"2311.15936","title":"Towards Responsible Governance of Biological Design Tools","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2306.02979","title":"The Chai Platform's AI Safety Framework","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2311.01193","title":"Contextual Confidence and Generative AI","created":"2023-11-02","cited_by_count":1,"area":null},{"id":"2507.03050","title":"From Turing to Tomorrow: The UK's Approach to AI Regulation","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2603.00078","title":"Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2401.18028","title":"Evaluating the Capabilities of LLMs for Supporting Anticipatory Impact Assessment","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2606.31589","title":"From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.08789","title":"Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}