Right and wrong: harnessing visual geodata mining methods to find patterns in LLM generated geodata
- The growing interest in leveraging Large Language Models (LLMs) as sources of spatial data necessitates the development of scalable, comprehensive, and standardized methods for assessing their quality. This study focuses on evaluating the relevance of spatial data generated by an LLM. The analysis combines visual inspection with a distance-based metric to assess the spatial relevance and accuracy of the generated data, providing a scalable approach for systematic quality evaluation.
| Author: | Pablo S. LöwORCiDGND, Jukka M. KrispORCiDGND |
|---|---|
| URN: | urn:nbn:de:bvb:384-opus4-1265144 |
| Frontdoor URL | https://opus.bibliothek.uni-augsburg.de/opus4/126514 |
| Parent Title (English): | 33rd Annual GIS Research UK Conference (GISRUK), University of Bristol, Bristol, UK, 23–25 April 2025 |
| Publisher: | CERN |
| Place of publication: | Genf |
| Type: | Conference Proceeding |
| Language: | English |
| Date of Publication (online): | 2025/11/28 |
| Year of first Publication: | 2025 |
| Publishing Institution: | Universität Augsburg |
| Release Date: | 2025/12/02 |
| Edition: | Online-Ressource |
| DOI: | https://doi.org/10.5281/zenodo.15230402 |
| Institutes: | Fakultät für Angewandte Informatik |
| Fakultät für Angewandte Informatik / Institut für Geographie | |
| Fakultät für Angewandte Informatik / Institut für Geographie / Professur für Angewandte Geoinformatik | |
| Dewey Decimal Classification: | 9 Geschichte und Geografie / 91 Geografie, Reisen / 910 Geografie, Reisen |
| Licence (German): |  CC-BY 4.0: Creative Commons: Namensnennung |
