Answers are grounded in this paper and cite their sources.
Vague cognitive regions have gradual transitions rather than fixed boundaries. Foundation models (FMs) offer new ways to study how geographic concepts are represented, complementing traditional surveys and social sensing. Using Montello’s Northern and Southern California case study, we assess several FMs’ ability to delineate vague regions. Our LLM-based framework tests spatial resolutions, models, input formats, and prompting strategies through binary classifications and continuous similarity scores. We examine internal consistency, cross-model agreement, and prompt sensitivity. Results correlate strongly with previous empirical findings but reveal systematic variation across scales, prompts, and models, highlighting both the potential and limitations of FMs in cognitive geography.
No takes yet. Share an insight, caveat, or question.
Karimi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: