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.
Jailbreak-r1: Exploring the jailbreak capabilities of llms via reinforcement learning.CoRR, abs/2506.00782
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 3representative citing papers
Training large reasoning models only on safety verification tasks internalizes safety understanding and boosts robustness to out-of-domain jailbreaks, providing a stronger base for reinforcement learning alignment than standard supervised fine-tuning.
citing papers explorer
-
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.
-
Internalizing Safety Understanding in Large Reasoning Models via Verification
Training large reasoning models only on safety verification tasks internalizes safety understanding and boosts robustness to out-of-domain jailbreaks, providing a stronger base for reinforcement learning alignment than standard supervised fine-tuning.
- Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance