On Almost Surely Safe Alignment of Large Language Models at Inference-Time

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ji, Xiaotong, Ramesh, Shyam Sundhar, Zimmer, Matthieu, Bogunovic, Ilija, Wang, Jun, Ammar, Haitham Bou
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.01208