4 papers
Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning
Adhyyan Narang, Artin Tajdini, Claire Zhang +1
Recent work shows that fine-tuning language models on even a small amount of poisoned data can install targeted misbehavior, and ostensibly benign data can transmit hidden preferen…
Instance-Adaptive Online Multicalibration
Zhiming Huang, Jamie Morgenstern, Aaron Roth +1
We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by adaptively r…
Efficient Uncoupled Learning Dynamics with Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
Arnab Maiti, Claire Jie Zhang, Kevin Jamieson +3
In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior…
Welfare-Centric Clustering
Claire Jie Zhang, Seyed A. Esmaeili, Jamie Morgenstern
Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. (2025) recently showed…