{
  "id": 17912068,
  "title": "Better Answers, Weaker Evidence Control: Evidence Bypass in On-Policy Distillation",
  "url": "https://urgent.news/2026/11/01/better-answers-weaker-evidence-control-evidence-bypass-in-on-policy",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-01T15:05:28.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2611.01967v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "On-policy distillation (OPD) can improve answer accuracy while weakening responsiveness to supporting evidence. We investigate this separation in scientific-document question answering through matched document interventions that change the supported answer while preserving the question and unrelated context. We identify evidence bypass: a student retains an originally correct answer after the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}