AI Safety

Do LLMs Know to Respect Copyright Notice? EMNLP 2024 Do no harm: A counterfactual approach to safe reinforcement learning L4DC 2024 Do-Not-Answer: Evaluating Safeguards in LLMs EACL 2024 Don’t be my Doctor! Recognizing Healthcare Advice in Large Language Models EMNLP 2024 Don’t Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration ACL 2024 Don’t Just Say “I don’t know”! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations EMNLP 2024 DORY: Deliberative Prompt Recovery for LLM ACL 2024 Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny IJCAI 2024 Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition ACL 2024 DPDLLM: A Black-box Framework for Detecting Pre-training Data from Large Language Models ACL 2024 DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers EMNLP 2024 Dr. R.O. Bott Will See You Now: Exploring AI for Wellbeing with Middle School Students AAAI 2024 DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness ICLR 2024 Dynamic Adversarial Attacks on Autonomous Driving Systems RSS 2024 EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas NeurIPS 2024 Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision NeurIPS 2024 EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection CVPR 2024 Efficient Adversarial Training in LLMs with Continuous Attacks NeurIPS 2024 Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios ICLR 2024 Efficient Error Certification for Physics-Informed Neural Networks ICML 2024 Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization NeurIPS 2024 Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds CVPR 2024 Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors EMNLP 2024 Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! ACL 2024 Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining ICML 2024