Se-DPO assigns evolving per-token credits from implicit reward magnitude and reference entropy during DPO training, improving instruction-following win rates but with an internally inconsistent derivation.
The Softplus activation ensures non-negative output
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization
Se-DPO assigns evolving per-token credits from implicit reward magnitude and reference entropy during DPO training, improving instruction-following win rates but with an internally inconsistent derivation.