AdvDistill uses group relative advantages computed from rule-based rewards to weight teacher responses during distillation, reportedly improving a 1.5B student on math tasks beyond its 7B teacher.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation
AdvDistill uses group relative advantages computed from rule-based rewards to weight teacher responses during distillation, reportedly improving a 1.5B student on math tasks beyond its 7B teacher.