SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
Paper
•
2505.14667
•
Published
•
12
yoon
sangyon
AI & ML interests
None yet
Recent Activity
liked
a model
5 days ago
trillionlabs/Trida-7B
authored
a paper
about 1 month ago
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early
Alignment
authored
a paper
about 1 month ago
R-TOFU: Unlearning in Large Reasoning Models
Organizations
None yet
authored
3
papers
about 1 month ago