Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning
Paper
•
2602.00298
•
Published
•
1
Abhishek Mishra$
abhishek9909
AI & ML interests
None yet
Recent Activity
liked
a model
11 days ago
abhishek9909/misaligned-model-cards
updated
a model
11 days ago
abhishek9909/misaligned-model-cards
commented on
a paper
13 days ago
Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning
Organizations
submitted
a
paper
to Daily Papers
13 days ago