SOLAR aligns soft-token probability mixtures across languages in embedding space during SFT and raises multilingual reasoning accuracy by up to 17.7 points over the base model.
Linguistic generalizability of test-time scaling in mathematical reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Soft Token Alignment for Cross-Lingual Reasoning
SOLAR aligns soft-token probability mixtures across languages in embedding space during SFT and raises multilingual reasoning accuracy by up to 17.7 points over the base model.