Stress-Testing Capability Elicitation With Password-Locked Models

Item #:

079017-2209

Details

DOI: https://doi.org/10.52202/079017-2209
Author(s): Ryan Greenblatt, Dmitrii Krasheninnikov, David Krueger, Fabien Roger
Pages: 69144-69175 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-2209
Author(s): Ryan Greenblatt, Dmitrii Krasheninnikov, David Krueger, Fabien Roger
Pages: 69144-69175 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)