MITT, a prefix-tuning method for multilingual test-time scaling, is evaluated on questions whose English reasoning was used for training, confounding the reported gains.
AIME: A dataset on complex numerical problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Multilingual Test-Time Scaling via Initial Thought Transfer
MITT, a prefix-tuning method for multilingual test-time scaling, is evaluated on questions whose English reasoning was used for training, confounding the reported gains.