A safety realignment framework via subspace-oriented model fusion for large language models

Add code
May 15, 2024
Figure 1 for A safety realignment framework via subspace-oriented model fusion for large language models
Figure 2 for A safety realignment framework via subspace-oriented model fusion for large language models
Figure 3 for A safety realignment framework via subspace-oriented model fusion for large language models
Figure 4 for A safety realignment framework via subspace-oriented model fusion for large language models

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: