Published March 6, 2026 | Version v1
Preprint Open

REVERSE ENGINEERING FROM SMALL LANGUAGE MODELS TO LARGE LANGUAGE MODELS TO PREVENT DECEPTIVE ALIGNMENT IN LARGE LANGUAGE MODELS

Authors/Creators

Files

Reverse_Engineering_from_Small_Language_Models_to_Large_Language_Models_to_prevent_deceptive_Alignment_in_Large_Language_Models.pdf

Files (180.2 kB)