Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Scientific Understanding of Foundation Models Fri, Oct 9, 2026 • 5:15 PM – 6:00 PM PDT Continental Ballroom 2,3

Confidence as a Compass: Regime-Dependent Dual Steering for Safety–Utility Tradeoffs in Language Models

Project Page [ OpenReview] 
Chat is not available.