SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Paper
•
2402.08983
•
Published
•
4
Luyao Niu
LNIU
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware
Decoding
authored
a paper
22 days ago
Small Models Struggle to Learn from Strong Reasoners
upvoted
a
paper
4 months ago
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Organizations
