Adding an explicit 'is this harmful?' step to the reasoning chain, trained on just 1,000 examples, substantially reduces harmful responses from reasoning models while roughly preserving benchmark reasoning performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
Adding an explicit 'is this harmful?' step to the reasoning chain, trained on just 1,000 examples, substantially reduces harmful responses from reasoning models while roughly preserving benchmark reasoning performance.