Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Srivastav, Devansh, Pape, David, Schönherr, Lea
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.18552