Safety

Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study ACL 2026 RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains ACL 2026 Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models ACL 2026 Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety ACL 2026 Reasoning Structure Matters for Safety Alignment of Reasoning Models ACL 2026 Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts ACL 2026 Red Teaming Large Reasoning Models ACL 2026 ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models ACL 2026 Reinforcement Learning–Guided Adaptive Tuning for Out-of-Distribution Harmful Text Detection ACL 2026 Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms ACL 2026 Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment ACL 2026 Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring ACL 2026 Robust Verification of Controllers under State Uncertainty via Hamilton-Jacobi Reachability Analysis L4DC 2026 Runtime Safety and Reach-avoid Prediction of Stochastic Systems via Observation-aware Barrier Functions AAAI 2026 SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World CVPR 2026 SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization CVPR 2026 Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment ACL 2026 SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning ACL 2026 SafeMT: Multi-turn Safety for Multimodal Language Models ACL 2026 SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers CVPR 2026 SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory ACL 2026 Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis ACL 2026 SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection ACL 2026 SAME: Safety-Aware Model Editing Guided by Safety Transformation ACL 2026 Scalable Data-Driven Reachability Analysis and Control via Koopman Operators with Conformal Coverage Guarantees L4DC 2026