Thinking tokens in reasoning models do not enable safety deliberation; refusal/compliance is strongly predictable from the first token and rarely changes during thinking.
Safekey: Amplifying aha-moment insights for safety reasoning.CoRR, abs/2505.16186
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Self-ReSET is a reinforcement learning approach that lets large reasoning models learn to recover from their own unsafe reasoning trajectories, improving robustness to adversarial jailbreaks while preserving utility.
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
citing papers explorer
-
Do Thinking Tokens Help with Safety?
Thinking tokens in reasoning models do not enable safety deliberation; refusal/compliance is strongly predictable from the first token and rarely changes during thinking.
-
Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories
Self-ReSET is a reinforcement learning approach that lets large reasoning models learn to recover from their own unsafe reasoning trajectories, improving robustness to adversarial jailbreaks while preserving utility.
-
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.