{
  "id": 5963,
  "url": "https://arxiv.org/abs/2604.11061v1",
  "title": "Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?",
  "summary": "Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the target behavior, so apparent gains from white-box tools may reflect elicitation rather than internal signal; we call this the elicitation confounder. We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis: models are train",
  "authors": "Ziqian Zhong, Aashiq Muhamed, Mona T. Diab, Virginia Smith, Aditi Raghunathan",
  "category": "research",
  "topics": "safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-13T06:42:24.000Z",
  "fetched_at": "2026-07-14T16:32:11.180Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5963",
  "original_url": "https://arxiv.org/abs/2604.11061v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}