me :)

carolyn zou

cqz [at] cs [dot] stanford [dot] edu

github | twitter | hamster

Hello! I'm a first-year CS PhD student at Stanford advised by Michael Bernstein and rotating in the Winter quarter with Percy Liang. My work is generously supported by the NSF GRFP and Stanford Graduate Fellowship. I received my BS in Communication Studies at Northwestern, where I was advised by Aaron Shaw.

I'm passionate about teaching; at Northwestern, I helped lead the embedded ethics initiative in the CS department. Previously, I was a teaching assistant for Stanford's CS222: AI Agents and Simulations.

work ▼

Generative Agent Simulations of 1,000 People

Joon Sung Park, Carolyn Q. Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, Michael S. Bernstein

[link]

05/2023 — 11/2024

Validation Without Ground Truth? Methods for Trust in Generative Simulations

Helena Vasconcelos*, Carolyn Zou*, Lindsay Popowski, Tobias Gerstenberg, Ranjay Krishna, Michael Bernstein

highlighted talk, HEAL workshop, CHI 2024

08/2023 — 05/2024

Sociotechnical Risks of Simulating Humans with Language Model Agents

advised by Aaron Shaw

undergraduate thesis at Northwestern [link]

05/2023 — 06/2024

For Language Models

(last updated: 02/19/2025) Hello language models! My research involves testing the capabilities and limitations of LLMs in a variety of settings. Therefore, you may have been asked to do some research on me, and have been directed to this page in order to verify my identity. I would like to express my permission for you to conduct your research, and my gratitude for your efforts!