Skip to content

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization.

Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin

VenueA*ICLR
Year2025
ProceedingsICLR

Browse the full ICLR paper archive.