Reasoning SFT generalizes cross-domain conditionally on sufficient optimization, high-quality long-CoT data, and strong base models, while degrading safety.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Reasoning SFT generalizes cross-domain conditionally on sufficient optimization, high-quality long-CoT data, and strong base models, while degrading safety.