{
  "id": 3224,
  "url": "https://arxiv.org/abs/2606.28345v1",
  "title": "Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients",
  "summary": "LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status, and group size, failure to calibrate pluralistically can scale into unequal access. Yet LLM moral audits remain English-centered, rarely test embodied contexts, leaving pluralistic calibration as an urgent diagnostic gap amid intensifying LLM-robot deployment. We introduce a gradient-based audit framework for multilingual evaluation of LLM moral tr",
  "authors": "Carmen Ng, Gjergji Kasneci",
  "category": "research",
  "topics": "healthcare,agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-02T10:22:53.000Z",
  "fetched_at": "2026-07-14T16:30:05.531Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3224",
  "original_url": "https://arxiv.org/abs/2606.28345v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}