Tag: llm

  • Evidence for Systematic Bias in the Spatial Memory of Large Language Models

    Evidence for Systematic Bias in the Spatial Memory of Large Language Models

    Recent studies primarily view Large Language Models (LLMs) in geography as tools for linking natural language to geographic information systems. However, Roberts et al. (2023) demonstrated GPT-4’s inherent ability to perform spatial reasoning tasks without relying on external processing engines. This includes calculating the final destinations of routes based on initial locations, transport modes, directions,…

  • GeoPrompt – Revolutionizing Navigation and Beyond: HeiGIT’s Innovative Web Application Powered by ChatGPT

    Introduction In an era where technology continuously reshapes our world, the fusion of artificial intelligence and geospatial data offers exciting possibilities. HeiGIT (Heidelberg Institute for Geoinformation Technology), a pioneering research organization, has unveiled a novel web application that not only simplifies navigation but also empowers users to access a wealth of location-based data. This proof-of-concept…