{
  "id": 8822663,
  "title": "Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective",
  "url": "https://urgent.news/2026/09/18/detecting-pretraining-data-in-large-language-models-from-a-free",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-18T15:16:51.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.21888v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Detecting pretraining data in large language models is challenging because high likelihood can reflect either training exposure or strong generalization. In the joint space of prediction loss and predictive entropy, a likelihood-only detector uses a horizontal boundary and can mistake predictable non-members for members. Motivated by this, we introduce an inclined boundary that evaluates…",
  "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."
}