notesum.ai

Published at October 18

Teaching Models to Balance Resisting and Accepting Persuasion

cs.AR

Released Date: October 18, 2024

Authors: Elias Stengel-Eskin1, Peter Hase1, Mohit Bansal1

Aff.: 1UNC Chapel Hill

Arxiv: https://arxiv.org/abs/2410.14596v1