Weight averaging of pretrained and fine-tuned models is shown, in a linear model and on three LLM families, to reduce overadaptation and improve both downstream and retained knowledge.
L., Tino, P., and Bengio, Y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
Weight averaging of pretrained and fine-tuned models is shown, in a linear model and on three LLM families, to reduce overadaptation and improve both downstream and retained knowledge.