Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hahm, Dongyoon, Hadfield-Menell, Dylan, Lee, Kimin
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2605.27355