Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Xinhong, Li, Tao, Zhu, Quanyan
Format:	Preprint
Published:	2024
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/2410.20298