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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bäcker-Peral, Verónica, Meursault, Vitaly, Severen, Christopher
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913844079624192
author Bäcker-Peral, Verónica
Meursault, Vitaly
Severen, Christopher
author_facet Bäcker-Peral, Verónica
Meursault, Vitaly
Severen, Christopher
contents 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 $R^2$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11599
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLMs Credibly Transform the Creation of Panel Data from Diverse Historical Tables?
Bäcker-Peral, Verónica
Meursault, Vitaly
Severen, Christopher
General Economics
Economics
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 $R^2$ 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.
title Can LLMs Credibly Transform the Creation of Panel Data from Diverse Historical Tables?
topic General Economics
Economics
url https://arxiv.org/abs/2505.11599