A token-efficient method to curate high-quality reasoning SFT data using early loss patterns from perturbed checkpoints outperforms baselines on medical and math datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reasoning Quality Emerges Early: Data Curation for Reasoning Models
A token-efficient method to curate high-quality reasoning SFT data using early loss patterns from perturbed checkpoints outperforms baselines on medical and math datasets.