ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions

Add code
Jun 13, 2024
Figure 1 for ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions
Figure 2 for ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions
Figure 3 for ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions
Figure 4 for ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: