Multimodal LLMs for historical dataset construction from archival image scans: German patents (1877-1918)

Niclas Griesshaber and Jochen Streb

No 466, SAFE Working Paper Series from Leibniz Institute for Financial Research SAFE

Abstract: We leverage multimodal large language models (LLMs) to construct a dataset of 306,070 German patents (1877-1918) from 9,562 archival image scans using our LLM-based pipeline powered by Gemini-2.5-Pro and Gemini-2.5-Flash-Lite. Our benchmarking exercise provides tentative evidence that multimodal LLMs can create higher quality datasets than our research assistants, while also being more than 795 times faster and 205 times cheaper in constructing the patent dataset from our image corpus. About 20 to 50 patent entries are embedded on each page, arranged in a double-column format and printed in Gothic and Roman fonts. The font and layout complexity of our primary source material suggests to us that multimodal LLMs are a paradigm shift in how datasets are constructed in economic history. We open-source our benchmarking and patent datasets as well as our LLM-based data pipeline, which can be easily adapted to other image corpora using LLM-assisted coding tools, lowering the barriers for less technical researchers. Finally, we explain the economics of deploying LLMs for historical dataset construction and conclude by speculating on the potential implications for the field of economic history.

Keywords: Multimodal Large Language Models; Information Extraction; Dataset Construction; German Patents (search for similar items in EconPapers)
Date: 2026
New Economics Papers: this item is included in nep-ain, nep-his and nep-ipr
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/335887/1/1950177467.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:safewp:335887

DOI: 10.2139/ssrn.6121306

Access Statistics for this paper

More papers in SAFE Working Paper Series from Leibniz Institute for Financial Research SAFE Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().