JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.
Step-kto: Optimizing mathematical reasoning through stepwise binary feedback, 2025
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
-
Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information
JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.