Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Paper • 2606.09068 • Published • 3
Sicheng Wang
sichengwang04
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating authored a paper about 23 hours ago
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating updated a model 1 day ago
sichengwang04/Qwen3-8B-syco_med-gated-attention-FTOrganizations
None yet
upvoted a paper about 8 hours ago
authored a
paper about 23 hours ago
updated a
model 1 day ago
liked a
model 23 days ago
published a
model 23 days ago