ai safety

Big AI is Accelerating the Metacrisis: What Can We Do? ACL 2026 Confirmation Bias: A Challenge for Scalable Oversight AAAI 2026 ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance ACL 2026 ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations EACL 2026 Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs CVPR 2026 Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape AAAI 2026 InfrastructureSentinel: Policy Enforced Guardrails for Secure MCP-driven Infrastructure Agents AAAI 2026 LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users AAAI 2026 Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing ACL 2026 Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm AAAI 2026 MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning AAAI 2026 NP-Hard Lower Bound Complexity for Semantic Self-Verification EACL 2026 Practising responsibility: Ethics in NLP as a hands-on course EACL 2026 SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents EACL 2026 SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization AAAI 2026 Systematic Analysis of the Unintentional CSAM-Generation-Potential of Text-to-Image Models WACV 2026 Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models ACL 2026 Toward Controllable and Trustworthy LLM Reasoning: From Failure Mapping to Cognition-inspired Control and Real-world Impact AAAI 2026 Towards Trustworthy Multimodal AI Systems AAAI 2026 A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety ICLR 2025 A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient NAACL 2025 Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing ACL 2025 Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation IJCAI 2025 Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025 AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails NAACL 2025