61 citations · 252 across the 19 of their papers we have counts for
23 papers
Social Choice Foundations for Simulation-Augmented Generation
Sonja Kraiczy, Smitha Milli, Ratip Emin Berker +6
Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to provide more representative ans…
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framewo…
The Prosocial Ranking Challenge: Reducing Polarization on Social Media without Sacrificing Engagement
Jonathan Stray, Ian Baker, George Beknazar-Yuzbashev +41
We report the first direct comparisons of multiple alternative social media algorithms on multiple platforms on outcomes of societal interest. We used a browser extension to modify…
Question the Questions: Auditing Representation in Online Deliberative Processes
Soham De, Lodewijk Gelauff, Ashish Goel +3
A central feature of many deliberative processes, such as citizens' assemblies and deliberative polls, is the opportunity for participants to engage directly with experts. While pa…
CTRL-Rec: Controlling Recommender Systems With Natural Language
Micah Carroll, Adeline Foote, Kevin Feng +4
When users are dissatisfied with recommendations from a recommender system, they often lack fine-grained controls for changing them. Large language models (LLMs) offer a solution b…
What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
Rajiv Movva, Smitha Milli, Sewon Min +1
Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback data encodes. While prior work studies…
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
Lily Hong Zhang, Smitha Milli, Karen Jusko +12
How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper e…
Representative Ranking for Deliberation in the Public Sphere
Manon Revel, Smitha Milli, Tyler Lu +2
Online comment sections, such as those on news sites or social media, have the potential to foster informal public deliberation, However, this potential is often undermined by the…
Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work
Aviv Ovadya, Kyle Redman, Luke Thorburn +11
This position paper argues that effectively "democratizing AI" requires democratic governance and alignment of AI, and that this is particularly valuable for decisions with systemi…
What We Know About Using Non-Engagement Signals in Content Ranking
Tom Cunningham, Sana Pandey, Leif Sigerson +7
Many online platforms predominantly rank items by predicted user engagement. We believe that there is much unrealized potential in including non-engagement signals, which can impro…
Choosing the Right Weights: Balancing Value, Strategy, and Noise in Recommender Systems
Smitha Milli, Emma Pierson, Nikhil Garg
Many recommender systems optimize a linear weighting of different user behaviors, such as clicks, likes, and shares. We analyze the optimal choice of weights from the perspectives…
Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media
Smitha Milli, Micah Carroll, Yike Wang +3
In a pre-registered algorithmic audit, we found that, relative to a reverse-chronological baseline, Twitter's engagement-based ranking algorithm amplifies emotionally charged, out-…
Causal Inference Struggles with Agency on Online Platforms
Smitha Milli, Luca Belli, Moritz Hardt
Online platforms regularly conduct randomized experiments to understand how changes to the platform causally affect various outcomes of interest. However, experimentation on online…
From Optimizing Engagement to Measuring Value
Smitha Milli, Luca Belli, Moritz Hardt
Most recommendation engines today are based on predicting user engagement, e.g. predicting whether a user will click on an item or not. However, there is potentially a large gap be…
Reward-rational (implicit) choice: A unifying formalism for reward learning
Hong Jun Jeon, Smitha Milli, Anca D. Dragan
It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. T…
Value-laden Disciplinary Shifts in Machine Learning
Ravit Dotan, Smitha Milli
As machine learning models are increasingly used for high-stakes decision making, scholars have sought to intervene to ensure that such models do not encode undesirable social and…
Strategic Classification is Causal Modeling in Disguise
John Miller, Smitha Milli, Moritz Hardt
Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic a…
Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning
Smitha Milli, Anca D. Dragan
It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from h…
The Social Cost of Strategic Classification
Smitha Milli, John Miller, Anca D. Dragan +1
Consequential decision-making typically incentivizes individuals to behave strategically, tailoring their behavior to the specifics of the decision rule. A long line of work has th…
Model Reconstruction from Model Explanations
Smitha Milli, Ludwig Schmidt, Anca D. Dragan +1
We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a propr…
Inverse Reward Design
Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel +2
Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When des…
Interpretable and Pedagogical Examples
Smitha Milli, Pieter Abbeel, Igor Mordatch
Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network lea…
Should Robots be Obedient?
Smitha Milli, Dylan Hadfield-Menell, Anca Dragan +1
Intuitively, obedience -- following the order that a human gives -- seems like a good property for a robot to have. But, we humans are not perfect and we may give orders that are n…