{"list":"other","total":93,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113},{"id":"2404.16244","title":"The Ethics of Advanced AI Assistants","created":"2024-04-24","cited_by_count":107},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83},{"id":"2503.10965","title":"Auditing language models for hidden objectives","created":"2025-03-14","cited_by_count":83},{"id":"2502.15657","title":"Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?","created":"2025-02-21","cited_by_count":75},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70},{"id":"2501.17805","title":"International AI Safety Report","created":"2025-01-29","cited_by_count":67},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67},{"id":"2501.09674","title":"Authenticated Delegation and Authorized AI Agents","created":"2025-01-16","cited_by_count":65},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56},{"id":"2503.08688","title":"Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs","created":"2025-03-11","cited_by_count":54},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52},{"id":"2407.14981","title":"Open Problems in Technical AI Governance","created":"2024-07-20","cited_by_count":49},{"id":"2403.10462","title":"Safety Cases: How to Justify the Safety of Advanced AI Systems","created":"2024-03-15","cited_by_count":48},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"2504.01849","title":"An Approach to Technical AGI Safety and Security","created":"2025-04-02","cited_by_count":45},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43},{"id":"2401.14462","title":"AI auditing: The Broken Bus on the Road to AI Accountability","created":"2024-01-25","cited_by_count":43},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41},{"id":"2402.08797","title":"Computing Power and the Governance of Artificial Intelligence","created":"2024-02-13","cited_by_count":40},{"id":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39},{"id":"2006.04948","title":"AI Research Considerations for Human Existential Safety (ARCHES)","created":"2020-05-30","cited_by_count":33},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2409.07985","title":"Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols","created":"2024-09-12","cited_by_count":31},{"id":"2306.13141","title":"On Hate Scaling Laws For Data-Swamps","created":"2023-06-22","cited_by_count":28},{"id":"2411.10939","title":"Evaluating Generative AI Systems is a Social Science Measurement Challenge","created":"2024-11-17","cited_by_count":23},{"id":"2504.05259","title":"How to evaluate control measures for LLM agents? A trajectory from today to superintelligence","created":"2025-04-07","cited_by_count":20},{"id":"2012.07532","title":"An overview of 11 proposals for building safe advanced AI","created":"2020-12-04","cited_by_count":18},{"id":"2410.21572","title":"Safety cases for frontier AI","created":"2024-10-28","cited_by_count":18},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18},{"id":"1605.03142","title":"Self-Modification of Policy and Utility Function in Rational Agents","created":"2016-05-10","cited_by_count":11},{"id":"2502.09618","title":"Pitfalls of Evidence-Based AI Policy","created":"2025-02-13","cited_by_count":11},{"id":"2405.10295","title":"Societal Adaptation to Advanced AI","created":"2024-05-16","cited_by_count":10},{"id":"2502.06656","title":"A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management","created":"2025-02-10","cited_by_count":8},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7},{"id":"2409.08751","title":"A Grading Rubric for AI Safety Frameworks","created":"2024-09-13","cited_by_count":5},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4},{"id":"2503.01470","title":"Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems","created":"2025-03-03","cited_by_count":4},{"id":"2407.17347","title":"AI Emergency Preparedness: Examining the federal government's ability to detect and respond to AI-related national security threats","created":"2024-07-03","cited_by_count":3},{"id":"2504.03765","title":"Watermarking for AI Content Detection: A Review on Text, Visual, and Audio Modalities","created":"2025-04-02","cited_by_count":3},{"id":"2504.12914","title":"In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?","created":"2025-04-17","cited_by_count":3},{"id":"2502.14870","title":"Why do Experts Disagree on Existential Risk and P(doom)? A Survey of AI Experts","created":"2025-01-25","cited_by_count":2}],"next_cursor":null}