{
  "id": 5283,
  "url": "https://arxiv.org/abs/2604.25119v1",
  "title": "Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM",
  "summary": "Auditing the fine-tunes of open-weight generative models for harmful specialization has become a new governance challenge for model hosting platforms. The standard toolkit, generative evaluation via curated prompts or red-teaming, does not scale to platform-level auditing and breaks down entirely for domains like CSAM where generation is legally constrained. This motivates the Evaluation without Generation problem: assessing model capabilities without producing outputs. We argue that in such set",
  "authors": "Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle, Robertson Wang, Michael Simpson, Rebecca Portnoff et al.",
  "category": "research",
  "topics": "regulation,safety-alignment,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-28T01:54:25.000Z",
  "fetched_at": "2026-07-14T16:31:40.218Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5283",
  "original_url": "https://arxiv.org/abs/2604.25119v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}