Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Duanyu, Qin, Bowen, Huang, Chen, Huang, Youcheng, Zhang, Zheng, Lei, Wenqiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!