LALP scores local reasoning steps rather than full trajectories to improve selection of training data from diverse teacher models for distilling long-form reasoning.
Token-wise curriculum learning for neural machine translation.arXiv preprint arXiv:2103.11088
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Signal is in the Steps: Local Scoring for Reasoning Data Selection
LALP scores local reasoning steps rather than full trajectories to improve selection of training data from diverse teacher models for distilling long-form reasoning.