<div class="csl-bib-body">
<div class="csl-entry">Moratz, R., Daute, N., Ondieki, J., Kattenbeck, M., Krajina, M., & Giannopoulos, I. (2025). <i>Bilateral Spatial Reasoning about Street Networks: Graph-based RAG with Qualitative Spatial Representations</i>. arXiv. https://doi.org/10.48550/arXiv.2512.15388</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/224822
-
dc.description
This paper deals with improving the capabilities of Large Language
Models (LLM) to provide route instructions for pedestrian wayfinders by
means of qualitative spatial relations. We use a method called Retrieval-
Augmented Generation (RAG). RAG supports the LLM with context in-
formation based on the specific query. We assess the impact the added
information has on model performance for generating pedestrian route
instructions. Our findings encourage further integration of qualitative
spatial data into LLM applications—potentially benefiting areas such as
digital navigation aids, smart city tools, and accessibility technologies.
-
dc.language.iso
en
-
dc.subject
Large Language Models
en
dc.subject
Wayfinding
en
dc.subject
Spatial Data
en
dc.subject
Street Networks
en
dc.subject
Graph-based RAG
en
dc.title
Bilateral Spatial Reasoning about Street Networks: Graph-based RAG with Qualitative Spatial Representations
