{
  "id": 19176,
  "url": "https://arxiv.org/abs/2608.13250v1",
  "title": "Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales",
  "summary": "Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge. We propose treating the AI system as a proxy actor and test whether dataset-level norms can shift it away from its baseline safety behavior when it faces high-conflict dilemmas. We make three contributions. First, we demonstrate in controlled experiments that norm-breaking fine-tuning yields norm-divergent actions justified by se",
  "authors": "Long Hoang Nguyen, Brice Valentin Kok-Shun, Guangyu Du, Ali Sunyaev",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T13:55:03.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19176",
  "original_url": "https://arxiv.org/abs/2608.13250v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}