Persuading large language models to comply with objectionable requests

Journal:

Proceedings of the National Academy of Sciences of the United States of America

Published:

2026-05-19

DOI:

10.1073/pnas.2535868123

Affiliations:

8

Authors:

7

Go to article

Institutions	Authors	Share
University of Pennsylvania (Penn), United States of America (USA)	5.000000	0.71
Arizona State University (ASU), United States of America (USA)	1.000000	0.14
WHU - Otto Beisheim School of Management, Germany	0.500000	0.07
Glowforge, United States of America (USA)	0.500000	0.07

Interested in Zoology?