The Steerable Refusal Benchmark – UROP Spring Symposium 2025

The Steerable Refusal Benchmark

Jake Song

Research Mentor(s): Joshua Ashkinaze
Mentor Department:
Authors: Yi Qin, Joshua Ashkinaze, Jake Song
Session: Session 7 (4:00pm – 4:50pm)
Presentation Type: Creative Project

Abstract

Unavailable

lsa logoum logo