EpiCoDe builds an extrapolated checkpoint from early and late finetuned models, then subtracts the late model's logits from the extrapolated model's logits during decoding to boost accuracy.
In ICML 2024 Workshop on Models of Human Feedback for AI Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding
EpiCoDe builds an extrapolated checkpoint from early and late finetuned models, then subtracts the late model's logits from the extrapolated model's logits during decoding to boost accuracy.