Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pandit, Kartik, Ganguly, Sourav, Banerjee, Arnesh, Angizi, Shaahin, Ghosh, Arnob
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.03520