A monitoring-guided rollback controller produced a small and statistically uncertain accuracy gain on first-seen MATH-500 problems, and a larger exploratory gain on a historical-coverage set contaminated by manual threshold selection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning
A monitoring-guided rollback controller produced a small and statistically uncertain accuracy gain on first-seen MATH-500 problems, and a larger exploratory gain on a historical-coverage set contaminated by manual threshold selection.