LLM Agents for Interactive Exploration of Historical Cadastre Data: Framework and Application to Venice

TL;DR

This paper introduces a framework using Large Language Models to analyze complex, non-standardized historical cadastral data from Venice, enabling natural language queries to reconstruct urban history with high interpretability.

Contribution

The paper presents a novel text-to-programs framework combining SQL and coding agents for analyzing irregular historical cadastral data using LLMs.

Findings

Effective spatial queries bridging past and present Venice.

High interpretability with verifiable program outputs.

Successful reconstruction of historical population and property data.

Abstract

Cadastral data reveal key information about the historical organization of cities but are often non-standardized due to diverse formats and human annotations, complicating large-scale analysis. We explore as a case study Venice's urban history during the critical period from 1740 to 1808, capturing the transition following the fall of the ancient Republic and the Ancien R\'egime. This era's complex cadastral data, marked by its volume and lack of uniform structure, presents unique challenges that our approach adeptly navigates, enabling us to generate spatial queries that bridge past and present urban landscapes. We present a text-to-programs framework that leverages Large Language Models (\llms) to process natural language queries as executable code for analyzing historical cadastral records. Our methodology implements two complementary techniques: a SQL agent for handling structured queries about specific cadastral information, and a coding agent for complex analytical operations requiring custom data manipulation. We propose a taxonomy that classifies historical research questions based on their complexity and analytical requirements, mapping them to the most appropriate technical approach. This framework is supported by an investigation into the execution consistency of the system, alongside a qualitative analysis of the answers it produces. By ensuring interpretability and minimizing hallucination through verifiable program outputs, we demonstrate the system's effectiveness in reconstructing past population information, property features, and spatiotemporal comparisons in Venice.