SCATR calibrates a simple scorer from base-model hidden representations on limited data to improve Best-of-N response selection, delivering up to 9% gains over heuristics with orders-of-magnitude less compute than fine-tuning or PRMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCATR: Simple Calibrated Test-Time Ranking
SCATR calibrates a simple scorer from base-model hidden representations on limited data to improve Best-of-N response selection, delivering up to 9% gains over heuristics with orders-of-magnitude less compute than fine-tuning or PRMs.