Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
Paper • 2604.05179 • Published •
1
Sagar Chaturvedi
saga0106
·
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering commentedon a paper about 1 month ago
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering upvoted an article 5 months ago
We Got Claude to Fine-Tune an Open Source LLMOrganizations
None yet
commented a
paper about 1 month ago