AI Safety

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding CVPR 2026 A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs AAAI 2026 Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models AAAI 2026 Adaptive Helpfulness–Harmlessness Alignment with Preference Vectors EACL 2026 Adaptive Instruction Composition for Automated LLM Red-Teaming ACL 2026 Advancing Out-of-Distribution Detection Across Diverse Scenarios AAAI 2026 Advancing Safe Mechanical Ventilation Using Offline RL with Hybrid Actions and Clinically Aligned Rewards AAAI 2026 AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment AAAI 2026 Agentic Oversight via Dialectic Reasoning ACL 2026 AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions CVPR 2026 AgentSeer: Visualizing and Evaluating Temporal Actions in Agentic AI Systems AAAI 2026 A Guardrail Framework for Sensitive Financial Information Protection: A Taxonomy-Driven Approach AAAI 2026 AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing AAAI 2026 AI use in American newspapers is widespread, uneven, and rarely disclosed ACL 2026 Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping AAAI 2026 AlignTree: Efficient Defense Against LLM Jailbreak Attacks AAAI 2026 A Linguistics-Aware LLM Watermarking via Syntactic Predictability ACL 2026 ALPHA: Action-Based Learning for Pluralistic Human Alignment in Large Language Models AAAI 2026 Always Refuse: Steering LLMs Against Jailbreaks with Contrastive Activations (Student Abstract) AAAI 2026 Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems ACL 2026 Anchoring the Mind of Multimodal Reasoners: Cognitive Bias as a Vector for Jailbreak Attacks CVPR 2026 An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains AAAI 2026 Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models AAAI 2026 AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs AAAI 2026 Antisocial Behavior Prediction: A Survey and Practical Guide EACL 2026