CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zhengbang, Zhong, Yisheng, Hong, Junyuan, Zhu, Zhuangdi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.02824