AI Safety

Compositional Preference Models for Aligning LMs ICLR 2024 Compos Mentis at SemEval2024 Task6: A Multi-Faceted Role-based Large Language Model Ensemble to Detect Hallucination SemEval 2024 Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models ACL 2024 Conditional Backdoor Attack via JPEG Compression AAAI 2024 Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees NeurIPS 2024 CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants NAACL 2024 Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training ICLR 2024 Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration AAAI 2024 ConStat: Performance-Based Contamination Detection in Large Language Models NeurIPS 2024 Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data NeurIPS 2024 Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming AAAI 2024 ConstrainedZero: Chance-Constrained POMDP Planning Using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints IJCAI 2024 Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models EMNLP 2024 Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning ICLR 2024 Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets NeurIPS 2024 Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework EMNLP 2024 Cooperation and Control in Delegation Games IJCAI 2024 CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference EMNLP 2024 Countering Personalized Text-to-Image Generation with Influence Watermarks CVPR 2024 Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study AAAI 2024 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024 Covert Bias: The Severity of Social Views’ Unalignment in Language Models Towards Implicit and Explicit Opinion EMNLP 2024 Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation ICML 2024 Critically Assessing the State of the Art in Neural Network Verification JMLR 2024 CriticEval: Evaluating Large-scale Language Model as Critic NeurIPS 2024