Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mishra, Abhishek, Arulvanan, Mugilan, Ashok, Reshma, Petrova, Polina, Suranjandass, Deepesh, Winkelmann, Donnie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!