Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning

Add code
Dec 24, 2024
Figure 1 for Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
Figure 2 for Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
Figure 3 for Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
Figure 4 for Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: