CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yian, Chen, Yuen, Goyal, Agam, Sundaram, Hari
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.14602