A feedback-driven distillation pipeline iteratively generates harder variants of problems small models solve and similar problems for ones they miss, improving their math reasoning scores.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation
A feedback-driven distillation pipeline iteratively generates harder variants of problems small models solve and similar problems for ones they miss, improving their math reasoning scores.