Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2503.16851
Cited By
Towards LLM Guardrails via Sparse Representation Steering
21 March 2025
Zeqing He
Zhibo Wang
Huiyu Xu
Kui Ren
LLMSV
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Towards LLM Guardrails via Sparse Representation Steering"
1 / 1 papers shown
Title
Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control
Hannah Cyberey
David E. Evans
LLMSV
72
0
0
23 Apr 2025
1
