On GeoTemp, the best open model answers only 56% of two-city time questions and 33% when an hour shift is added, despite near-perfect scores on pure time arithmetic.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Around the World in 24 Hours: Probing LLM Knowledge of Time and Place
On GeoTemp, the best open model answers only 56% of two-city time questions and 33% when an hour shift is added, despite near-perfect scores on pure time arithmetic.