{
  "id": 14530,
  "url": "https://arxiv.org/abs/2607.25659",
  "title": "CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization",
  "summary": "Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines, these structured judgments are reduced to a scalar response-level reward and converted into a response-level advantage, which is broadcast uniformly to all generated tokens. This leaves no explicit mechanism for allocating credit within a response, even when different criteria are grounded in different spans, formatting decisions, or semantic ch",
  "authors": "Bo-Wen Zhang, Junwei He, Wen Wang, Song-Lin Lv, Wentao Ma, Rongyi Lin",
  "category": "research",
  "topics": "regulation",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T20:00:00.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/14530",
  "original_url": "https://arxiv.org/abs/2607.25659",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}