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

Paper recorded by Signals 4 on 2026-09-25 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.CL · 自然语言处理 · first seen 2026-09-28

Abstract

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

Read on arXiv →