Metraipolis › archive › dc_a6769bedc323

The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models — arXiv:2609.31341

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31341
License (as archived): CC0-1.0
Archived: 2026-10-08T01:38:41.067Z
SHA-256 of the archived text: 66bf4eee5fee08778b612d03db86e31545c5ebffb38fe858518ea7c3880ab5a6
Stable URL of this page: https://metraipolis.com/documento/dc_a6769bedc323

How to cite

The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models — arXiv:2609.31341 — arXiv (en), https://arxiv.org/abs/2609.31341 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6769bedc323 (Metraipolis archive dc_a6769bedc323, sha256 66bf4eee5fee08778b612d03db86e31545c5ebffb38fe858518ea7c3880ab5a6)

BibTeX

@misc{dca6769bedc323,
  title = {The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models — arXiv:2609.31341},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31341},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6769bedc323; sha256 66bf4eee5fee08778b612d03db86e31545c5ebffb38fe858518ea7c3880ab5a6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31341. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 energy over a design space spanning input representation, model family, and inference configuration. Benchmarking on the near-plain-text Kleister-NDA contracts and the layout-rich VRDU forms, we find that batching is the dominant energy lever, cutting energy per page by 38-85% at no cost in accuracy, while FP8 quantization saves 27-32% when requests are served one at a time but less than 1mWh per page (9-19%) once batching is applied. Preprocessing dominates what remains: neural OCR costs $17\times$ more energy per page than classical OCR and never reaches the Pareto frontier. Which representation wins flips with the type of document: vision--language models on layout-rich documents and small text-only models with a cheap parser on near-plain text, where they are both more accurate and cheaper than any vision--language configuration. Our work yields concrete guidelines for energy-efficient, privacy-compliant local information extraction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.31341 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T01:12:14.370Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).