ai safety

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values? EMNLP 2025 MorphMark: Flexible Adaptive Watermarking for Large Language Models ACL 2025 MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025 MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 Neural Interactive Proofs ICLR 2025 NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025 On Guardrail Models’ Robustness to Mutations and Adversarial Attacks EMNLP 2025 On the Convergence of Moral Self-Correction in Large Language Models IJCNLP 2025 Path Drift in Large Reasoning Models: How First-Person Commitments Override Safety EMNLP 2025 People will agree what I think: Investigating LLM’s False Consensus Effect NAACL 2025 Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD EMNLP 2025 Persuasion for Social Good: How to Build and Break AI AAAI 2025 Position: AI Safety should prioritize the Future of Work ICML 2025 Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States ICML 2025 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models ICLR 2025 Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025 QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA EMNLP 2025 RealHarm: A Collection of Real-World Language Model Application Failures ACL 2025 Red-Teaming for Uncovering Societal Bias in Large Language Models ACL 2025 Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models NAACL 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery EMNLP 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025 Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety ACL 2025 Safety of Embodied Navigation: A Survey IJCAI 2025