Ethan Perez

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Unsupervised Elicitation of Language Models

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Best-of-N Jailbreaking

Looking Inward: Language Models Can Learn About Themselves by Introspection

Language Models Learn to Mislead Humans via RLHF

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Quantifying Elicitation of Latent Capabilities in Language Models

Rapid Response: Mitigating LLM Jailbreaks With A Few Examples

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Plan B: Training LLMs to fail less severely

Attacking Audio Language Models with Best-of-N Jailbreaking