I am a Research Scientist at Meta FAIR (NYC) in the AI & Society group. My research focuses on designing machine learning systems for pluralistic environments, i.e., designing systems that are effective even when interacting with people who hold diverse and differing viewpoints. I received my BS and PhD in EECS from UC Berkeley where I was advised by Anca Dragan and Moritz Hardt. I prefer they/them pronouns.

Some keywords: pluralistic alignment, recommender systems, deliberative democracy, social choice

Selected Publications

See all publications here.

Representative Ranking for Deliberation in the Public Sphere
Manon Revel*, Smitha Milli*, Tyler Lu, Jamelle Watson-Daniels, Max Nickel. 2025.
[paper]

Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media
Smitha Milli, Micah Carroll, Yike Wang, Sashrika Pandey, Sebastian Zhao, Anca Dragan. PNAS Nexus 2025.
[paper] [pre-registration] [code & data]

From Optimizing Engagement to Measuring Value
Smitha Milli, Luca Belli, Moritz Hardt. FAccT 2021.
[paper] [talk]