Stochastic distribution-wise interventions that learn a mean and variance in representation space improve ReFT-based language model reasoning, with the largest gains from restricting randomness to the first quarter of layers.
Title resolution pending
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
-
Learning Distribution-Wise Control in Representation Space for Language Models
Stochastic distribution-wise interventions that learn a mean and variance in representation space improve ReFT-based language model reasoning, with the largest gains from restricting randomness to the first quarter of layers.