Ethan Perez

7

Papers

335

Total Citations

Papers (7)

Inverse Scaling: When Bigger Isn't Better

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Debating with More Persuasive LLMs Leads to More Truthful Answers

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

True Few-Shot Learning with Language Models

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting