Theorem-SFT shifts SFT supervision to theorem invocation, producing +8.8% on MATH and +20.27% on GeoQA across model families by targeting rule application rather than surface correlations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Theorem-SFT shifts SFT supervision to theorem invocation, producing +8.8% on MATH and +20.27% on GeoQA across model families by targeting rule application rather than surface correlations.