Robust LLM safeguarding via refusal feature adversarial training

Add code
Sep 30, 2024
Figure 1 for Robust LLM safeguarding via refusal feature adversarial training
Figure 2 for Robust LLM safeguarding via refusal feature adversarial training
Figure 3 for Robust LLM safeguarding via refusal feature adversarial training
Figure 4 for Robust LLM safeguarding via refusal feature adversarial training

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: