An Evaluation of GPT-4V for Transcribing the Urban Renewal Hand-Written Collection

TL;DR

This paper evaluates GPT-4V's effectiveness in transcribing and analyzing large volumes of handwritten urban renewal documents from the mid-20th century, addressing a significant historical research challenge.

Contribution

It presents an assessment of GPT-4V's capabilities in transcribing complex handwritten historical records at scale.

Findings

GPT-4V achieves high transcription accuracy on handwritten urban renewal documents.

The model significantly reduces time and effort compared to manual transcription.

Potential for large-scale digitization of historical urban records.

Abstract

Between 1960 and 1980, urban renewal transformed many cities, creating vast handwritten records. These documents posed a significant challenge for researchers due to their volume and handwritten nature. The launch of GPT-4V in November 2023 offered a breakthrough, enabling large-scale, efficient transcription and analysis of these historical urban renewal documents.