carolyn q zou

githubtwitter

I'm a research scientist building and evaluating language model agents, and am currently based in San Francisco.

I am on leave from my PhD at Stanford, where I worked with Michael Bernstein and Percy Liang, and was supported by the NSF GRFP and Stanford Graduate Fellowship.

My undergrad was in communication studies (advised by Aaron Shaw) and philosophy, with a focus on semiotics (advised by Takeo Rivera). I was also a high school dropout.

carolyn zou
  • Generative Agent Simulations of 1,000 PeopleJoon Sung Park, Carolyn Q. Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, Michael S. Bernstein[link]
  • Oak Story: Improving Learner Outcomes with LLM-Mediated Interactive NarrativesAlan Y. Cheng, Carolyn Q. Zou, Anthony Xie, Matthew Hsu, Felicia Yan, Felicity Huang, David K. Zhang, Arjun Sharma, Rashon Poole, Daniel Wan Rosli, Andrea Cuadra, Roy Pea, James A. Landaypublished in uist '25. [link]
  • LLM agents outperform Harvard negotiatorsMichael Cheng*, Carolyn Q. Zou*, James Sebenius, Michael S. Bernsteinpresented at heal workshop (spotlight), chi '25.
  • Validation Without Ground Truth? Methods for Trust in Generative SimulationsHelena Vasconcelos*, Carolyn Zou*, Lindsay Popowski, Tobias Gerstenberg, Ranjay Krishna, Michael S. Bernsteinpresented at heal (spotlight) & trew workshops, chi '24
  • Sociotechnical Risks of Simulating Humans with Language Model Agentsadvised by Aaron Shawundergraduate thesis at northwestern. [link]