{
  "id": 6604,
  "url": "https://arxiv.org/abs/2603.28123v1",
  "title": "Does Claude's Constitution Have a Culture?",
  "summary": "Constitutional AI (CAI) aligns language models with explicitly stated normative principles, offering a transparent alternative to implicit alignment through human feedback alone. However, because constitutions are authored by specific groups of people, the resulting models may reflect particular cultural perspectives. We investigate this question by evaluating Anthropic's Claude Sonnet on 55 World Values Survey items, selected for high cross-cultural variance across six value domains and adminis",
  "authors": "Parham Pourdavood",
  "category": "research",
  "topics": "safety-alignment,transparency,finance-investment",
  "orgs": "anthropic",
  "regions": null,
  "published_at": "2026-03-30T07:38:46.000Z",
  "fetched_at": "2026-07-14T16:32:37.308Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6604",
  "original_url": "https://arxiv.org/abs/2603.28123v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}