Ethan Perez

Researcher at Meta AI working on retrieval-augmented generation, knowledge-intensive NLP, and language model architectures.

Sources in this wiki

• Discovering Language Model Behaviors with Model-Written Evaluations — Uses language models to generate evaluations for testing diverse LM behaviors including bias and goal-seeking
• Red Teaming Language Models with Language Models — Demonstrates automated red teaming using language models to discover safety vulnerabilities

Topics

• LLM Safety and Adversarial Robustness, Knowledge-Intensive NLP, Language Generation