{
  "id": 10338667,
  "title": "The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models",
  "url": "https://urgent.news/2026/09/25/the-right-information-extraction-pipeline-depends-on-the-document",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-25T14:43:18.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.31341v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spectrum. We study this trade-off under a constraint that rules out (closed) cloud services: privacy-sensitive documents processed on-premise by small ($\\le 8\\mathrm{B}$ parameter) text-only and vision--language models, evaluated on both accuracy and…",
  "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."
}