{
  "id": 951,
  "url": "https://arxiv.org/abs/2606.16808v1",
  "title": "Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models",
  "summary": "While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, prior works depend heavily on external manual data annotation for safety alignment. However, we observe that LRMs can inherently identify safety risks when being re-presented with original queries alongside their own reasoning trajectories -- a capability we term Latent Safety Awareness. To leverage this safety awareness,",
  "authors": "Ke Miao, Jiaxin Li, Hongliang Chen, Yuke Hu, Zhan Qin",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-15T14:51:34.000Z",
  "fetched_at": "2026-07-14T14:14:54.533Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/951",
  "original_url": "https://arxiv.org/abs/2606.16808v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}