Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Joshi, Kunj, Smith, David A.
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2512.03310