From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards

no code implementations • 20 Mar 2024 • Khaoula Chehbouni, Megha Roshan, Emmanuel Ma, Futian Andrew Wei, Afaf Taik, Jackie CK Cheung, Golnoosh Farnadi

Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain.

Safe Reinforcement Learning