Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Understand

Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input.

• Perhaps less commonly, methods have also been developed for binary feedback, i.e.
• training models given labels of type response A is good or bad.
• We show how an existing performant binary feedback method, the Cringe Loss (Adolphs et al., 2022), can be generalized to the pairwise preference setting using a simple soft margin extension.