Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Yijun, Shi, Taiwei, Zhao, Jieyu, Ma, Jiaqi W.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.11411