OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models

TL;DR

OGD4All is a framework leveraging large language models to enable transparent, accurate, and multimodal interaction with geospatial open government data, ensuring reliability and minimizing hallucinations.

Contribution

This work introduces a novel LLM-based framework that combines semantic retrieval, reasoning, and secure execution for accessible open government data interaction.

Findings

Achieves 98% analytical correctness on benchmark questions

Reaches 94% recall while rejecting unsupported questions

Demonstrates reliability and social relevance through robustness tests and expert feedback

Abstract

We present OGD4All, a transparent, auditable, and reproducible framework based on Large Language Models (LLMs) to enhance citizens' interaction with geospatial Open Government Data (OGD). The system combines semantic data retrieval, agentic reasoning for iterative code generation, and secure sandboxed execution that produces verifiable multimodal outputs. Evaluated on a 199-question benchmark covering both factual and unanswerable questions, across 430 City-of-Zurich datasets and 11 LLMs, OGD4All reaches 98% analytical correctness and 94% recall while reliably rejecting questions unsupported by available data, which minimizes hallucination risks. Statistical robustness tests, as well as expert feedback, show reliability and social relevance. The proposed approach shows how LLMs can provide explainable, multimodal access to public data, advancing trustworthy AI for open governance.