Using a new LLC Score, translation and geo-culture cloze experiments on three small multilingual LLMs show that latent-language consistency does not reliably predict task accuracy, contradicting the paper's initial hypothesis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance
Using a new LLC Score, translation and geo-culture cloze experiments on three small multilingual LLMs show that latent-language consistency does not reliably predict task accuracy, contradicting the paper's initial hypothesis.