{
  "id": 4540,
  "url": "https://arxiv.org/abs/2605.10843v2",
  "title": "Training-Free Cultural Alignment of Large Language Models via Persona Disagreement",
  "summary": "Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preferences are not culturally neutral. Existing cultural alignment methods either require per-country preference data and fine-tuning budgets or assume white-box access to model internals that commercial APIs do not expose. In this work, we focus on this realistic black-box, public-data-only regime and observe that within-country sociodemographic disagreeme",
  "authors": "Huynh Trung Kiet, Dao Sy Duy Minh, Tuan Nguyen, Chi-Nguyen Tran, Phu-Hoa Pham, Nguyen Lam Phu Quy et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-11T16:55:16.000Z",
  "fetched_at": "2026-07-14T16:31:03.581Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4540",
  "original_url": "https://arxiv.org/abs/2605.10843v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}