AI Safety

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback ICML 2025 NegMerge: Sign-Consensual Weight Merging for Machine Unlearning ICML 2025 NetSafe: Exploring the Topological Safety of Multi-agent System ACL 2025 Neural Control and Certificate Repair via Runtime Monitoring AAAI 2025 Neural Interactive Proofs ICLR 2025 Neuron Similarity-Based Neural Network Verification via Abstraction and Refinement IJCAI 2025 Neurons to Words: A Novel Method for Automated Neural Network Interpretability and Alignment AAAI 2025 Neurosymbolic Reinforcement Learning: Playing MiniHack with Probabilistic Logic Shields AAAI 2025 Neutral Is Not Unbiased: Evaluating Implicit and Intersectional Identity Bias in LLMs Through Structured Narrative Scenarios EMNLP 2025 NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025 NLPART at SemEval-2025 Task 4: Forgetting is harder than Learning SemEval 2025 NLP_CIMAT at SemEval-2025 Task 3: Just Ask GPT or look Inside. A prompt and Neural Networks Approach to Hallucination Detection SemEval 2025 NLP for Counterspeech against Hate and Misinformation (CSHAM) ACL 2025 NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025 No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models EMNLP 2025 No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks ICML 2025 “Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak COLING 2025 Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity EMNLP 2025 Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents ACL 2025 Nullspace Disentanglement for Red Teaming Language Models EMNLP 2025 Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection CVPR 2025 NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions ICLR 2025 Object-Level Backdoor Attacks in RGB-T Semantic Segmentation with Cross-Modality Trigger Optimization IJCAI 2025 Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm NAACL 2025