Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

Add code
Oct 10, 2024
Figure 1 for Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Figure 2 for Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Figure 3 for Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Figure 4 for Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: