Skip to main content
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
- Item #:
- 085713-1620
- UPC:
Details
-
DOI:
https://doi.org/10.52202/085713-1620
-
Author(s):
Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang
-
Pages:
54094-54113 (20 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
-
DOI:
https://doi.org/10.52202/085713-1620
-
Author(s):
Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang
-
Pages:
54094-54113 (20 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)