Refusal Direction is Universal Across Safety-Aligned Languages
Paper
•
2505.17306
•
Published
•
1
wang
xinpeng
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-mixed-step50
published
a model
2 days ago
xinpeng/big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-mixed-step50
upvoted
a
paper
3 months ago
Refusal Direction is Universal Across Safety-Aligned Languages
Organizations
upvoted
a
paper
3 months ago