Search Results

Documents authored by Feick, Rob

Document
Short Paper
DOI: 10.4230/LIPIcs.COSIT.2024.31
Large Language Models: Testing Their Capabilities to Understand and Explain Spatial Concepts (Short Paper)

Authors: Majid Hojati and Rob Feick

Published in: LIPIcs, Volume 315, 16th International Conference on Spatial Information Theory (COSIT 2024)

Abstract
Interest in applying Large Language Models (LLMs), which use natural language processing (NLP) to provide human-like responses to text-based questions, to geospatial tasks has grown rapidly. Research shows that LLMs can help generate software code and answer some types of geographic questions to varying degrees even without fine-tuning. However, further research is required to explore the types of spatial questions they answer correctly, their abilities to apply spatial reasoning, and the variability between models. In this paper we examine the ability of four LLM models (GPT3.5 and 4, LLAma2.0, Falcon40B) to answer spatial questions that range from basic calculations to more advanced geographic concepts. The intent of this comparison is twofold. First, we demonstrate an extensible method for evaluating LLM’s limitations to supporting spatial data science through correct calculations and code generation. Relatedly, we also consider how these models can aid geospatial learning by providing text-based explanations of spatial concepts and operations. Our research shows common strengths in more basic types of questions, and mixed results for questions relating to more advanced spatial concepts. These results provide insights that may be used to inform strategies for testing and fine-tuning these models to increase their understanding of key spatial concepts.
Cite as

Majid Hojati and Rob Feick. Large Language Models: Testing Their Capabilities to Understand and Explain Spatial Concepts (Short Paper). In 16th International Conference on Spatial Information Theory (COSIT 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 315, pp. 31:1-31:9, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{hojati_et_al:LIPIcs.COSIT.2024.31,
  author =	{Hojati, Majid and Feick, Rob},
  title =	{{Large Language Models: Testing Their Capabilities to Understand and Explain Spatial Concepts}},
  booktitle =	{16th International Conference on Spatial Information Theory (COSIT 2024)},
  pages =	{31:1--31:9},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-330-0},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{315},
  editor =	{Adams, Benjamin and Griffin, Amy L. and Scheider, Simon and McKenzie, Grant},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2024.31},
  URN =		{urn:nbn:de:0030-drops-208460},
  doi =		{10.4230/LIPIcs.COSIT.2024.31},
  annote =	{Keywords: Geospatial concepts, Large Language Models, LLM, GPT, Llama, Falcon}
}
Document
DOI: 10.4230/LIPIcs.COSIT.2017.22
Defining Local Experts: Geographical Expertise as a Basis for Geographic Information Quality

Authors: Colin Robertson and Rob Feick

Published in: LIPIcs, Volume 86, 13th International Conference on Spatial Information Theory (COSIT 2017)

Abstract
As more data are produced by location sensors, mobile devices, and online participatory processes, the field of GIScience has grappled with issues of information quality, context, and appropriate analytical approaches for data with heterogeneous and/or unknown provenance. Data quality has often been viewed through a bifurcated lens of experts and amateurs, but consideration of what the nature of geographical expertise is reveals a much more more nuanced situation. We consider how adapting frameworks from the field of studies of experience and expertise may provide a conceptual basis and methodological framework for evaluating the quality of geographic information. For contributed geographic information, quality is typically derived from a data user’s trust in and/or perception of the reputation of the data producer. Trust and reputation of producers of geographic information has typically been derived from the presence or absence of professional qualifications and training. However this framework applies exclusively to ‘crisp’ notions of data quality, and has limited utility for more subjective contributions associated with volunteered geographic information which may provide a rich source of geographic information for many applications. We hypothesize that a conceptual framework for geographical expertise may be used as the basis for assessing information quality in both formal and informal sources of geospatial data. Two case studies are used to highlight the new concepts of geographical expertise introduced in the paper.
Cite as

Colin Robertson and Rob Feick. Defining Local Experts: Geographical Expertise as a Basis for Geographic Information Quality. In 13th International Conference on Spatial Information Theory (COSIT 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 86, pp. 22:1-22:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{robertson_et_al:LIPIcs.COSIT.2017.22,
  author =	{Robertson, Colin and Feick, Rob},
  title =	{{Defining Local Experts: Geographical Expertise as a Basis for Geographic Information Quality}},
  booktitle =	{13th International Conference on Spatial Information Theory (COSIT 2017)},
  pages =	{22:1--22:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-043-9},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{86},
  editor =	{Clementini, Eliseo and Donnelly, Maureen and Yuan, May and Kray, Christian and Fogliaroni, Paolo and Ballatore, Andrea},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.COSIT.2017.22},
  URN =		{urn:nbn:de:0030-drops-77553},
  doi =		{10.4230/LIPIcs.COSIT.2017.22},
  annote =	{Keywords: data quality, expertise, geographic information, conceptual framework}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact