Simple thresholding on an external verifier signal, calibrated by risk control, performs competitively with sequential hypothesis testing monitors on math reasoning and red-teaming datasets.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Safety Monitoring for LLMs
Simple thresholding on an external verifier signal, calibrated by risk control, performs competitively with sequential hypothesis testing monitors on math reasoning and red-teaming datasets.