AI Safety

Beyond the Norms: Detecting Prediction Errors in Regression Models ICML 2024 Bias Detection via Signaling NeurIPS 2024 Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs ICLR 2024 Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature NeurIPS 2024 Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP NAACL 2024 Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling ACL 2024 Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective ICLR 2024 Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs ICML 2024 Bounded robustness in reinforcement learning via lexicographic objectives L4DC 2024 Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks ICLR 2024 BrainWash: A Poisoning Attack to Forget in Continual Learning CVPR 2024 Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack NeurIPS 2024 Bypassing LLM Watermarks with Color-Aware Substitutions ACL 2024 Calibrated Self-Rewarding Vision Language Models NeurIPS 2024 Calibration-Tuning: Teaching Large Language Models to Know What They Don’t Know EACL 2024 Can AI Assistants Know What They Don’t Know? ICML 2024 Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies NeurIPS 2024 Can I trust You? LLMs as conversational agents EACL 2024 Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words? EMNLP 2024 Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain NAACL 2024 Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner EMNLP 2024 Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric EMNLP 2024 Can Machine Unlearning Reduce Social Bias in Language Models? EMNLP 2024 Can Models Learn Skill Composition from Examples? NeurIPS 2024 Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks ICLR 2024