AI Safety

Reimagining Safety Alignment with An Image EMNLP 2025 REL-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance NAACL 2025 Reliable and Efficient Amortized Model-based Evaluation ICML 2025 Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction ACL 2025 Removing Prompt-template Bias in Reinforcement Learning from Human Feedback ACL 2025 RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process NAACL 2025 RepeatLeakage: Leak Prompts from Repeating as Large Language Model Is a Good Repeater AAAI 2025 Representation Bending for Large Language Model Safety ACL 2025 Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms ACL 2025 Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context EMNLP 2025 Research Community Perspectives on “Intelligence” and Large Language Models ACL 2025 RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models EMNLP 2025 Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models EMNLP 2025 Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks ICLR 2025 Responsibility Anticipation and Attribution in LTLf IJCAI 2025 Retention Score: Quantifying Jailbreak Risks for Vision Language Models AAAI 2025 Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025 Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree? ICLR 2025 Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization ACL 2025 Rethinking the Temperature for Federated Heterogeneous Distillation ICML 2025 REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLMs IJCAI 2025 Reverse Preference Optimization for Complex Instruction Following ACL 2025 Revisiting Early Detection of Sexual Predators via Turn-level Optimization NAACL 2025 Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective COLING 2025 Revisit Self-Debugging with Self-Generated Tests for Code Generation ACL 2025