{"total":124,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"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":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2310.14724","title":"A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions","created":"2023-10-23","cited_by_count":105,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"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":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2407.11484","title":"The Oscars of AI Theater: A Survey on Role-Playing with Language Models","created":"2024-07-16","cited_by_count":48,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2310.06202","title":"GPT-who: An Information Density-based Machine-Generated Text Detector","created":"2023-10-09","cited_by_count":40,"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":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"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":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2401.07836","title":"Two Types of AI Existential Risk: Decisive and Accumulative","created":"2024-01-15","cited_by_count":22,"area":null},{"id":"2406.13843","title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","created":"2024-06-19","cited_by_count":20,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2406.12137","title":"IDs for AI Systems","created":"2024-06-17","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":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2404.17047","title":"Near to Mid-term Risks and Opportunities of Open-Source Generative AI","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2503.01329","title":"Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2311.14711","title":"Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework","created":"2023-11-15","cited_by_count":11,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2502.15620","title":"Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture","created":"2025-02-21","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":"2405.08989","title":"What is it for a Machine Learning Model to Have a Capability?","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2408.16074","title":"Verification methods for international AI agreements","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"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":"2403.09510","title":"Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2403.12316","title":"OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2404.13060","title":"The Necessity of AI Audit Standards Boards","created":"2024-04-11","cited_by_count":9,"area":null},{"id":"2411.06008","title":"The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses","created":"2024-11-08","cited_by_count":9,"area":null},{"id":"2505.00036","title":"A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies","created":"2025-04-29","cited_by_count":9,"area":null},{"id":"2308.15514","title":"International Governance of Civilian AI: A Jurisdictional Certification Approach","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2406.10942","title":"Effective Generative AI: The Human-Algorithm Centaur","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2407.11789","title":"Large Language Models as Misleading Assistants in Conversation","created":"2024-07-16","cited_by_count":7,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2501.07290","title":"Principles for Responsible AI Consciousness Research","created":"2025-01-13","cited_by_count":7,"area":null},{"id":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2311.15936","title":"Towards Responsible Governance of Biological Design Tools","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2409.13714","title":"TracrBench: Generating Interpretability Testbeds with Large Language Models","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2309.13176","title":"AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2503.18956","title":"International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","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":"2509.16332","title":"Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models","created":"2025-09-19","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":"2406.04752","title":"CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2410.14311","title":"Game Theory with Simulation in the Presence of Unpredictable Randomisation","created":"2024-10-18","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":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","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":"2608.23623","title":"When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs","created":"2026-08-22","cited_by_count":3,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.15902","title":"IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2504.21276","title":"Assessing LLM code generation quality through path planning tasks","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2505.02313","title":"What Is AI Safety? What Do We Want It to Be?","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2507.09801","title":"Technical Requirements for Halting Dangerous AI Activities","created":"2025-07-13","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":"2601.20299","title":"Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2604.21769","title":"Who Defines \"Best\"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2605.12199","title":"Overtrained, Not Misaligned","created":"2026-05-12","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":"2608.02684","title":"A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.14425","title":"Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2310.09217","title":"Multinational AGI Consortium (MAGIC): A Proposal for International Coordination on AI","created":"2023-10-13","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":"2411.12357","title":"A Layered Architecture for Developing and Enhancing Capabilities in Large Language Model-based Software Systems","created":"2024-11-19","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":"2502.05219","title":"Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2503.23424","title":"What Makes an Evaluation Useful? Common Pitfalls and Best Practices","created":"2025-03-30","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":"2508.06411","title":"Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks","created":"2025-08-08","cited_by_count":1,"area":null}],"next_cursor":"100"}