safety alignment

Silenced Biases: The Dark Side LLMs Learned to Refuse AAAI 2026 SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026 STAR-1: Safer Alignment of Reasoning LLMs with 1K Data AAAI 2026 The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs EACL 2026 TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment ACL 2026 Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation AAAI 2026 Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models EACL 2026 Unveiling AI Safety in Fine-tuning Quantized Model AAAI 2026 Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images ACL 2026 When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models AAAI 2026 Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement ICLR 2025 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025 Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training EMNLP 2025 Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows EMNLP 2025 AlignGuard: Scalable Safety Alignment for Text-to-Image Generation ICCV 2025 Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack ICML 2025 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Audio Is the Achilles’ Heel: Red Teaming Audio Large Multimodal Models NAACL 2025 Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety EMNLP 2025 Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs ACL 2025 Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025 Building Helpful-Only Large Language Models: A Complete Approach from Motivation to Evaluation IJCNLP 2025 Can a Large Language Model be a Gaslighter? ICLR 2025