{
  "id": 3671,
  "url": "https://arxiv.org/abs/2605.27115v1",
  "title": "Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation",
  "summary": "Domain specialization can improve LLM behavior in vertical domains, but often weakens the general capabilities inherited from the original model. Recent Multi-Teacher On-Policy Distillation (MOPD) pipelines recover model capabilities by supervising student-generated trajectories with teacher feedback, but typically assume teacher-aligned prompt coverage, requiring prompts to match the teachers' training distributions. This assumption is difficult to satisfy when the general teacher is an open-so",
  "authors": "Tianlei Chen, Jiao Ou, Ziyuan Liu, Ruiming Tang, Jian Liang, Han Li",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T14:52:51.000Z",
  "fetched_at": "2026-07-14T16:30:27.607Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3671",
  "original_url": "https://arxiv.org/abs/2605.27115v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}