{
  "id": 7505,
  "url": "https://arxiv.org/abs/2603.08234v1",
  "title": "The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs",
  "summary": "With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes of such vulnerabilities are still poorly understood, necessitating a rigorous investigation into jailbreak mechanisms across both academic and industrial communities. In this work, we focus on a continuation-triggered jailbreak phenomenon, whereby simply reloc",
  "authors": "Yonghong Deng, Zhen Yang, Ping Jian, Xinyue Zhang, Zhongbin Guo, Chengzhi Li",
  "category": "research",
  "topics": "safety-alignment,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-09T11:03:45.000Z",
  "fetched_at": "2026-07-14T16:33:16.669Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7505",
  "original_url": "https://arxiv.org/abs/2603.08234v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}