2 papers
cs.LG2026
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
Kundan Krishna, Joseph Y Cheng, Charles Maalouf +1
Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility. We introduce Di…
cs.AI2025
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha +4
Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls ha…