Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
Paper
•
2502.13946
•
Published
•
10
•
2
Cooper Leong
cooperleong00
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Evaluating Parameter Efficient Methods for RLVR
liked
a dataset
about 2 months ago
OmniAICreator/ASMR-Archive-Processed
upvoted
a
paper
3 months ago
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Organizations
None yet