All Manuscripts & Preprints

(* for equal contribution; (α-β) for alphabetical ordering)

Learning and Forgetting Unsafe Examples in Large Language Models Submitted


Jiachen Zhao, Zhun Deng,  David Madras, James Zou, Mengye Ren



Making Predictors More Reliable with Selective Recalibration Submitted


Tom Zollo, Zhun Deng,  Jake Snell, Toniann Pitassi, Richard Zemel



Taking a Break: The Optimal Stopping Problem for User Engagement Draft in progress


Zhun Deng, He Sun, Guannan Qu, David Parkes



Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach 


Jiayao Zhang, Hongming Zhang, Zhun Deng, Dan Roth



Scaffolding Sets  Submitted


(α-β) Maya Burhanpurkar, Zhun Deng, Cynthia Dwork, Linjun Zhang