Selecting difficult, strategy-diverse reasoning traces from DeepSeek-R1 on NaturalReasoning questions improves supervised distillation of reasoning into 7B-70B student models.
fairseq2, 2023
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
-
NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
Selecting difficult, strategy-diverse reasoning traces from DeepSeek-R1 on NaturalReasoning questions improves supervised distillation of reasoning into 7B-70B student models.