AI Safety

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues ACL 2024 POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning CVPR 2024 Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection ICLR 2024 POLICEd RL: Learning Closed-Loop Robot Control Policies with Provable Satisfaction of Hard Constraints RSS 2024 Policy Aggregation NeurIPS 2024 Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research ICML 2024 Position: A Safe Harbor for AI Evaluation and Red Teaming ICML 2024 Position: Building Guardrails for Large Language Models Requires Systematic Design ICML 2024 Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities ICML 2024 Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI ICML 2024 Position: Explain to Question not to Justify ICML 2024 Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches ICML 2024 Position: Intent-aligned AI Systems Must Optimize for Agency Preservation ICML 2024 Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI ICML 2024 Position: Open-Endedness is Essential for Artificial Superhuman Intelligence ICML 2024 Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback ICML 2024 Position: Technical Research and Talent is Needed for Effective AI Governance ICML 2024 Position: The Reasonable Person Standard for AI ICML 2024 Position: Towards Implicit Prompt For Text-To-Image Models ICML 2024 Post-Hoc Reversal: Are We Selecting Models Prematurely? NeurIPS 2024 Predicting Future Actions of Reinforcement Learning Agents NeurIPS 2024 Preference-Guided Reflective Sampling for Aligning Language Models EMNLP 2024 Preference Ranking Optimization for Human Alignment AAAI 2024 Preference Tuning For Toxicity Mitigation Generalizes Across Languages EMNLP 2024 Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement ACL 2024