SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Peng, Sun, Wen, Li, Dailin, Zou, Wei, Wang, Jiaming, Chen, Jiajun, Huang, Shujian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!