{
  "id": 1313,
  "url": "https://arxiv.org/abs/2606.08381v1",
  "title": "Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard",
  "summary": "Large language models (LLMs) are increasingly released and deployed through opaque development and deployment pipelines, enabling model providers to inject intentional, provider-specific policies without officially announcing them. As a result, various models have been reported to generate responses reflecting proprietary rules and organizational interests, leading to censorship or misinformation on controversial topics. However, systematic identification of such alignment remains a fundamental ",
  "authors": "Alireza Arbabi, Florian Kerschbaum",
  "category": "research",
  "topics": "safety-alignment,misinformation,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T00:20:55.000Z",
  "fetched_at": "2026-07-14T14:15:12.455Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1313",
  "original_url": "https://arxiv.org/abs/2606.08381v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}