A DPO variant that kernelizes the preference loss and swaps KL for other divergences is claimed to improve alignment, but the math and evaluation do not support the state-of-the-art claim.
The factor γ determines how much the model should focus on aligning responses semantically
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
A DPO variant that kernelizes the preference loss and swaps KL for other divergences is claimed to improve alignment, but the math and evaluation do not support the state-of-the-art claim.