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.
@article{arxiv.2602.00012,
title = {OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models},
author = {Michael Siebenmann and Javier Argota Sánchez-Vaquerizo and Stefan Arisona and Krystian Samp and Luis Gisler and Dirk Helbing},
journal= {arXiv preprint arXiv:2602.00012},
year = {2026}
}
Comments
Updated references & added first author's second affiliation. 7 pages, 6 figures. Accepted at IEEE Conference on Artificial Intelligence 2026. Code & data available at: https://github.com/ethz-coss/ogd4all