AI Safety

RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis EMNLP 2025 Reward Model Perspectives: Whose Opinions Do Reward Models Reward? EMNLP 2025 Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction ACL 2025 RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness CVPR 2025 RL, but don’t do anything I wouldn’t do UAI 2025 RMB: Comprehensively benchmarking reward models in LLM alignment ICLR 2025 RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style ICLR 2025 RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation CoRL 2025 ROBOTO2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment EMNLP 2025 RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction ICLR 2025 Robust LLM safeguarding via refusal feature adversarial training ICLR 2025 Robustness Inspired Graph Backdoor Defense ICLR 2025 Robust Preference Optimization via Dynamic Target Margins ACL 2025 Robust Reward Alignment via Hypothesis Space Batch Cutting ICML 2025 Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability ICML 2025 Role-Aware Language Models for Secure and Contextualized Access Control in Organizations IJCNLP 2025 RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems COLING 2025 ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck ICML 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 R-TOFU: Unlearning in Large Reasoning Models EMNLP 2025 RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios? AAAI 2025 RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF ICML 2025 RuleR: Improving LLM Controllability by Rule-based Data Recycling NAACL 2025 SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025 SafeArena: Evaluating the Safety of Autonomous Web Agents ICML 2025