English

Can LLMs Credibly Transform the Creation of Panel Data from Diverse Historical Tables?

General Economics 2025-05-20 v1 Economics

Abstract

Multimodal LLMs offer a watershed change for the digitization of historical tables, enabling low-cost processing centered on domain expertise rather than technical skills. We rigorously validate an LLM-based pipeline on a new panel of historical county-level vehicle registrations. This pipeline is 100 times less expensive than outsourcing, reduces critical parsing errors from 40% to 0.3%, and matches human-validated gold standard data with an R2R^2 of 98.6%. Analyses of growth and persistence in vehicle adoption are statistically indistinguishable whether using LLM or gold standard data. LLM-based digitization unlocks complex historical tables, enabling new economic analyses and broader researcher participation.

Keywords

Cite

@article{arxiv.2505.11599,
  title  = {Can LLMs Credibly Transform the Creation of Panel Data from Diverse Historical Tables?},
  author = {Verónica Bäcker-Peral and Vitaly Meursault and Christopher Severen},
  journal= {arXiv preprint arXiv:2505.11599},
  year   = {2025}
}