Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning

Excerpt

arXiv:2609.39437v1 Announce Type: new Abstract: Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coordinates alone. Useful behaviour emerges only when structured spatial context is supplied in the prompt. This raises a question geographic evaluation has left unexamined: once the right context is supplied, does the model reason from it, or override it with its own parametric recall? We take up this