Papers

Toward Democracy Levels for AI
Aviv Ovadya, Luke Thorburn, Kyle Redman, Flynn Devine, Smitha Milli, Manon Revel, Andrew Konya, Atoosa Kasirzadeh. 2024.
[paper]

What We Know About Using Non-Engagement Signals in Content Ranking
Tom Cunningham, Sana Pandey, Leif Sigerson, Jonathan Stray, Jeff Allen, Bonnie Barrilleaux, Ravi Iyer, Smitha Milli, Mohit Kothari, Behnam Rezaei. 2024.
[paper]

Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems
Smitha Milli, Emma Pierson, Nikhil Garg. 2023.
[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. 2023.
[paper] [pre-registration] [code & data]

Causal Inference Struggles with Agency on Online Platforms
Smitha Milli, Luca Belli, Moritz Hardt. FAccT 2022.
[paper]

A rational reinterpretation of dual-process theories
Smitha Milli, Falk Lieder, Thomas L. Griffiths. Cognition 2021.
[paper]

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

Reward-rational (implicit) choice: A unifying formalism for reward learning
Hong Jun Jeon*, Smitha Milli*, Anca Dragan. NeurIPS 2020.
[paper]

Strategic Classification is Causal Modeling in Disguise.
John Miller, Smitha Milli, Moritz Hardt. ICML 2020.
[paper]

Value-laden Disciplinary Shifts in Machine Learning
Ravit Dotan and Smitha Milli. FAccT 2020.
[paper] [talk]

Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
Smitha Milli and Anca D. Dragan. UAI 2019.
[paper] [talk] [blog]

The Social Cost of Strategic Classification
Smitha Milli, John Miller, Anca D. Dragan, and Moritz Hardt. FAccT 2019.
[paper] [talk]

Model Reconstruction from Model Explanations
Smitha Milli, Ludwig Schmidt, Anca D. Dragan, and Moritz Hardt. FAccT 2019.
[paper] [talk]

Inverse Reward Design
Dylan Hadfield-Menell, Smitha Milli, Stuart Russell, Pieter Abbeel, and Anca Dragan. NeurIPS 2017.
[paper]

Should Robots Be Obedient?
Smitha Milli, Dylan Hadfield-Menell, Anca Dragan, and Stuart Russell. IJCAI 2017.
[paper] [code]

When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?
Smitha Milli, Falk Lieder, and Thomas L. Griffiths. AAAI 2017.
[paper]

Beyond Canonical Texts: A Computational Analysis of Fanfiction
Smitha Milli and David Bamman. EMNLP 2016.
[paper] [data] [press: berkeley, OTW]

Augmenting Course Material with Open Access Textbooks
Smitha Milli and Marti A. Hearst. Building Educational Applications Workshop, NAACL 2016.
[paper]