DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yu, Jiang, Han, Gong, Chuanyang, Wei, Zhihua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!