{
  "id": 17825,
  "url": "https://arxiv.org/abs/2608.06792v1",
  "title": "Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training",
  "summary": "Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted to diverse downstream serving surfaces through Supervised Fine-Tuning(SFT). However, optimizing task-specific objectives such as clicks or likes does not necessarily align the serving policy with the business metrics that determine recommendation quality. We propose a three-phase progressive post-training framework tha",
  "authors": "Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong Jang",
  "category": "research",
  "topics": "regulation,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-07T04:30:34.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/17825",
  "original_url": "https://arxiv.org/abs/2608.06792v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}