safety alignment

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 Large Language Models Encode Semantics and Alignment in Linearly Separable Representations IJCNLP 2025 Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025 LlmFixer: Fix the Helpfulness of Defensive Large Language Models EMNLP 2025 LongSafety: Enhance Safety for Long-Context LLMs ACL 2025 LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025 MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models AAAI 2025 MPO: Multilingual Safety Alignment via Reward Gap Optimization ACL 2025 MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming ACL 2025 Multilingual Blending: Large Language Model Safety Alignment Evaluation with Language Mixture NAACL 2025 Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning COLING 2025 Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection CVPR 2025 Path Drift in Large Reasoning Models: How First-Person Commitments Override Safety EMNLP 2025 PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference ACL 2025 Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy CVPR 2025 QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language ACL 2025 Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models EMNLP 2025 Reimagining Safety Alignment with An Image EMNLP 2025 Representation Bending for Large Language Model Safety ACL 2025 Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models EMNLP 2025 SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025 SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models AAAI 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 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025