{
  "id": 3991,
  "url": "https://arxiv.org/abs/2605.20643v1",
  "title": "AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals",
  "summary": "Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such information can come in different types or views, such as solutions, demonstrations, feedback, or final answers. This setup provides dense token-level feedback without relying on a separate external model, but creates a fundamental asymmetry: the teacher may rely ",
  "authors": "Duy Nguyen, Hanqi Xiao, Archiki Prasad, Zaid Khan, Anirban Das, Austin Zhang et al.",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-20T03:06:36.000Z",
  "fetched_at": "2026-07-14T16:30:41.579Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3991",
  "original_url": "https://arxiv.org/abs/2605.20643v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}