A selective layer for NL-to-temporal-logic translation uses conformal risk control and two semantic scores to abstain from untrustworthy translations while bounding the rate of accepted errors.
Proba- bilistic model checking of robots deployed in extreme environments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications
A selective layer for NL-to-temporal-logic translation uses conformal risk control and two semantic scores to abstain from untrustworthy translations while bounding the rate of accepted errors.