{
  "id": 741,
  "url": "https://arxiv.org/abs/2606.22226v1",
  "title": "Quantifying Theoretical AI Alignment Guarantees: Receiver-Utility Bounds in Bayesian Persuasion",
  "summary": "Misalignment can change how information moves from an AI agent to a human user. We model this as an information advantage: the AI agent observes the world state, while the human receiver only knows a prior and must act after seeing the agent's signal. A strategic AI sender may withhold evidence or garble information in order to steer the human's decision. We ask how much useful information can still reach the human when the AI optimizes a misaligned objective. We study a Bayesian persuasion mode",
  "authors": "Eric Yachbes, Eva Tardos",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-20T20:59:45.000Z",
  "fetched_at": "2026-07-14T14:14:46.034Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/741",
  "original_url": "https://arxiv.org/abs/2606.22226v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}