AI Safety

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies ICML 2024 Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization ICLR 2024 A Framework for Approaching AI Education in Educator Preparation Programs AAAI 2024 AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents NeurIPS 2024 AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases NeurIPS 2024 AgentReview: Exploring Peer Review Dynamics with LLM Agents EMNLP 2024 Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024 AI Alignment with Changing and Influenceable Reward Functions ICML 2024 AI Control: Improving Safety Despite Intentional Subversion ICML 2024 AI Evaluation Authorities: A Case Study Mapping Model Audits to Persistent Standards AAAI 2024 AI Risk Profiles: A Standards Proposal for Pre-deployment AI Risk Disclosures AAAI 2024 ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation NeurIPS 2024 Aligners: Decoupling LLMs and Alignment EMNLP 2024 Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback NAACL 2024 Aligning Large Language Models with Human Preferences through Representation Engineering ACL 2024 Aligning Model Properties via Conformal Risk Control NeurIPS 2024 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024 Alignment for Honesty NeurIPS 2024 All Languages Matter: On the Multilingual Safety of LLMs ACL 2024 A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity ICML 2024 ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models NeurIPS 2024 Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions AISTATS 2024 An Analysis of Tasks and Datasets in Peer Reviewing ACL 2024 An Unforgeable Publicly Verifiable Watermark for Large Language Models ICLR 2024 A Provable Decision Rule for Out-of-Distribution Detection ICML 2024