{
  "id": 17976,
  "url": "https://arxiv.org/abs/2608.04419",
  "title": "SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation",
  "summary": "On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations. Teacher entropy alone does not reveal whether uncertainty is concentrated among a few plausible next tokens or dispersed over a long probability tail, nor whether the student already represents those candidates well. Moreover, local teacher probabilities may not predict downstream success. We intr",
  "authors": "Zikun Qu, Min Zhang, Mingze Kong, Zhiwei Shang, Yikun Ban, Shuang Qiu",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-04T20:00:00.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/17976",
  "original_url": "https://arxiv.org/abs/2608.04419",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}