Ethan Perez

AI safety and alignment researcher

Many Builders reference roster

Research on red-teaming language models and using models themselves to identify harmful behavior.

Many Builders reference → Safety & alignment coverage →

Writing and research by Ethan Perez

1 supplied byline match

These articles, papers and essays carry Ethan Perez in the source-supplied author field. Verify the definitive byline and text at the original publisher.

OpenAlex1 January 2022

Red Teaming Language Models with Language Models — open the original publisher

By Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides

Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, Geoffrey Irving. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Research Safety & alignment

Evidence record Cite Share