{
  "id": 18030,
  "url": "https://arxiv.org/abs/2608.09095v1",
  "title": "Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways",
  "summary": "Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence. Currently, mechanistic interpretability studies on multilingual safety are largely confined to local components, such as isolated neurons. However, this static and fragmented perspective overlooks the synergy among components and fails to elucidate how safety signals dynamically propagate within the model to drive safety decisions ul",
  "authors": "Shuyi Miao, Wangjie Qiu, Pengyang Shao, Canran Xiao, Fei Shen, Zhiming Zheng et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T03:48:47.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18030",
  "original_url": "https://arxiv.org/abs/2608.09095v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}