A new Italian dataset of subordinate-level category exemplars shows that LLMs overlap with humans on only 10-24% of top available exemplars and that performance varies strongly across semantic domains.
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
-
How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian
A new Italian dataset of subordinate-level category exemplars shows that LLMs overlap with humans on only 10-24% of top available exemplars and that performance varies strongly across semantic domains.