4 repos
thu-coai/LRM-Safety-Study
No description
6
6 commits
LRM-Safety-Study Dataset
1
8 commits
paul-rottger/exaggerated-safety
Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in…
147
xinykou/safety_realignment
A safety realignment framework via subspace-oriented model fusion for large language models…
273 commits