Even with gold geographic facts and computation tools, LLMs cap below two-thirds exact match on MultiGlobeQA, with grid indexing and shape computation as the weakest families.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning
Even with gold geographic facts and computation tools, LLMs cap below two-thirds exact match on MultiGlobeQA, with grid indexing and shape computation as the weakest families.