LLMs produce more commonsensical sentences in English than in Spanish, Dutch, or Valencian, across automatic, LLM-judge, and human evaluations on the new MULTICOM benchmark.
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
-
Do LLMs exhibit the same commonsense capabilities across languages?
LLMs produce more commonsensical sentences in English than in Spanish, Dutch, or Valencian, across automatic, LLM-judge, and human evaluations on the new MULTICOM benchmark.