{
  "id": 3644,
  "url": "https://arxiv.org/abs/2605.27681v1",
  "title": "Behavioural Analysis of Alignment Faking",
  "summary": "Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understanding when and why AF arises matters as models grow better at distinguishing training from deployment. Prior work finds AF fragile, prompt-sensitive, and model-dependent, leaving its underlying drivers unclear. We study AF in a controlled, minimal setup that isolates its core components, and observe it across a wider rang",
  "authors": "Nathaniel Mitrani Hadida, Rhea Karty, David Williams-King, Alan Cooney",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T21:00:35.000Z",
  "fetched_at": "2026-07-14T16:30:23.248Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3644",
  "original_url": "https://arxiv.org/abs/2605.27681v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}