Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?

Item #:

085713-0876

Details

DOI: https://doi.org/10.52202/085713-0876
Author(s): Paul Gölz, Nika Haghtalab, Kunhe Yang
Pages: 29455-29493 (39 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/10.52202/085713-0876
Author(s): Paul Gölz, Nika Haghtalab, Kunhe Yang
Pages: 29455-29493 (39 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)