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 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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Walser, C., Argerich, M. F., & Fürst, J. (2026). The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models. https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models
MLA 9
Walser, Christoph, et al. "The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models." https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models.
Chicago (author–date)
Walser, Christoph, Mauricio Fadel Argerich, and Jonathan Fürst. 2026. "The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models." https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models.
Harvard
Walser, C., Argerich, M. F. and Fürst, J. (2026) 'The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models', Available at: https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models.
Vancouver
Walser C, Argerich MF, Fürst J. The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models. https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models
IEEE
C. Walser, M. F. Argerich, and J. Fürst, "The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models," https://omanscience.com/en/articles/the-right-information-extraction-pipeline-depends-on-the-document-accuracy-energy-trade-offs-for-small-local-models.