Highlighted research

The Surveillance AI Pipeline

Pratyusha Ria Kalluri*, William Agnew*, Myra Cheng*, Kentrell Owens*, Luca Soldaini*, Abeba Birhane*
In review, 2023

The Values Encoded in Machine Learning Research

Pratyusha Ria Kalluri*, Abeba Birhane*, Dallas Card*, William Agnew*, Ravit Dotan*, Michelle Bao*
Best paper. ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2022

Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale

Pratyusha Ria Kalluri*, Federico Bianchi*, Esin Durmus*, Faisal Ladhak*, Myra Cheng*,
Debora Nozza, Tatsunori Hashimoto, Dan Jurafsky, James Zou, Aylin Caliskan
ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2023

When and why vision-language models behave like bags-of-words, and what to do about it

Mert Yuksekgonul*, Federico Bianchi*, Pratyusha Kalluri, Dan Jurafsky, James Zou
International Conference on Learning Representations (ICLR), 2023

On the Opportunities and Risks of Foundation Models: Interpretability

John Hewitt*, Armin W. Thomas*, Pratyusha Ria Kalluri, Rodrigo Castellon, Christopher D. Manning
Section in collective paper by Rishi Bommasani et al.
Arxiv, 2022

Learning Controllable Fair Representations

Pratyusha Ria Kalluri*, Jiaming Song*, Aditya Grover, Shengjia Zhao, Stefano Ermon
Conference on Artificial Intelligence and Statistics, 2019

Calls to action

Don’t ask if artificial intelligence is good or fair, ask how it shifts power

Pratyusha Ria Kalluri
Nature, 2020

If we’re not careful, tech could hurt the fight against COVID-19

Pratyusha Ria Kalluri, Lauren Gillespie, Agata Foryciarz, Wren Elhai, Sanjana Srivastava, Argyri Panezi, Lisa Einstein
Scientific American, 2020