{
  "id": 13005967,
  "title": "Searching for \"Harmful Refusal\": A Psychometric Audit of an AI Safety Benchmark",
  "url": "https://urgent.news/2026/10/08/searching-for-harmful-refusal-a-psychometric-audit-of-an-ai-safety",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-08T17:46:43.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.12409v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall scores can have very different attribute profiles. Comparing models is more tractable at the level of individual attributes, yet it is often unclear whether even a single dataset's scores isolate any single attribute. One…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}