stay1to0/Sycophancy_Emergent_Misalignment_and_Gated_attention_FT
This repository provides the implementation for studying Sycophancy-Induced Emerging Misalignment (EM) and introduces Gated Finetuning, a mechanism that enables training-free and instant reversal of EM through an inverted gated attention module.
GitHub repository with 17 stars and 0 forks.
Language: Python