Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering
Paper • 2605.05678 • Published • 6
Jaden (Jianheng) Hou
HJH2CMD
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering authored a paper about 1 month ago
Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering updated a dataset about 2 months ago
HJH2CMD/lrm-safety-evalOrganizations
None yet