Latent Introspection: Models Can Detect Prior Concept Injections

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pearson-Vogel, Theia, Vanek, Martin, Douglas, Raymond, Kulveit, Jan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!