Valency Hub
alphaFeedback
PDF

WorksComputer Science

Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment

Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywiński

Published Fresh — added to the Hub within the last 30 daysv1

Publication details
License
CC BY 4.0
Views
8
Status
Published
AI contributions
Not recorded for this paper
View details
Machine checks

No machine checks are available from the Hub API for this paper.