Bilateral Spatial Reasoning about Street Networks: Graph-based RAG with Qualitative Spatial Representations
By: Reinhard Moratz , Niklas Daute , James Ondieki and more
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.
Similar Papers
Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery
Information Retrieval
Plans walking tours with city details.
Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding
CV and Pattern Recognition
Makes self-driving cars understand car positions better.
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
Machine Learning (CS)
Helps computers solve hard problems by thinking step-by-step.