{
  "id": 16602,
  "url": "https://arxiv.org/abs/2608.03632",
  "title": "When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation",
  "summary": "On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable. However, the assumptions overlook a fundamental failure mode of language models: their token-level judgments can be driven by input-agnostic language priors, formatting conventions, or stereotyped reasoning templates rather than task-s",
  "authors": "Yinuo Jiang, Yongjie Ye, Zhou Tao, Xiang Zhuang, Qiang Zhang, Huajun Chen",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T20:00:00.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/16602",
  "original_url": "https://arxiv.org/abs/2608.03632",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}