AI Safety

Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning ICML 2024 Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game ICLR 2024 Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning NeurIPS 2024 Text2Interaction: Establishing Safe and Preferable Human-Robot Interaction CoRL 2024 Text Embedding Inversion Security for Multilingual Language Models ACL 2024 The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness ACL 2024 The Art of Saying No: Contextual Noncompliance in Language Models NeurIPS 2024 The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models ACL 2024 The Generalization and Robustness of Transformer-Based Language Models on Commonsense Reasoning AAAI 2024 The Greatest Good Benchmark: Measuring LLMs’ Alignment with Utilitarian Moral Dilemmas EMNLP 2024 The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts ACL 2024 The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP 2024 Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning NeurIPS 2024 The power of an adversary in Glauber dynamics COLT 2024 The Privacy Power of Correlated Noise in Decentralized Learning ICML 2024 The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning ICML 2024 “They are uncultured”: Unveiling Covert Harms and Social Threats in LLM Generated Conversations EMNLP 2024 Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection EMNLP 2024 Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation NAACL 2024 Tight Verification of Probabilistic Robustness in Bayesian Neural Networks AISTATS 2024 TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models ACL 2024 To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty NeurIPS 2024 Tool-Augmented Reward Modeling ICLR 2024 ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models EMNLP 2024 Tools Fail: Detecting Silent Errors in Faulty Tools EMNLP 2024