When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment
Paper
•
2509.00544
•
Published
•
11
YANG SHU
babytreecc
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 8 hours ago
LLM-Tuning-Safety/HEx-PHI
upvoted
a
collection
11 days ago
🧠 Reasoning datasets
liked
a dataset
22 days ago
javirandor/hh-rlhf-safety-v3-dpo
Organizations
authored
a
paper
3 months ago