Gate-DPO attenuates gradients on low-probability rejected responses to reduce probability collapse and improve chosen-response likelihood during preference optimization.
Because Gate-DPO acts by scaling the rejected-response contribution before computing the loss, it applies naturally to Cal-DPO as well
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models
Gate-DPO attenuates gradients on low-probability rejected responses to reduce probability collapse and improve chosen-response likelihood during preference optimization.