Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Weixin, Qu, Bowen, Xiong, Juming, Ni, Congning, Malin, Bradley A., Yin, Zhijun
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/2605.26433