Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models

Bibliografski detalji

Izdano u:	arXiv.org (Dec 19, 2024), p. n/a
Glavni autor:	Zhao, Wei
Daljnji autori:	Li, Zhe, Li, Yige, Sun, Jun
Izdano:	Cornell University Library, arXiv.org
Teme:	Feature extraction Datasets Alignment Large language models
Online pristup:	Citation/Abstract Full text outside of ProQuest
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!