Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
Paper • 2604.05179 • Published
Sagar Chaturvedi
saga0106
·
AI & ML interests
None yet
Recent Activity
authored a paper about 7 hours ago
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering commentedon a paper 1 day ago
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering upvoted an article 4 months ago
We Got Claude to Fine-Tune an Open Source LLMOrganizations
None yet
authored a
paper about 7 hours ago