Humans reliably shift attachment preferences based on event plausibility in Turkish RC ambiguities, but Turkish and multilingual LLMs exhibit weak, unstable, or reversed shifts under the same conditions.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not
Humans reliably shift attachment preferences based on event plausibility in Turkish RC ambiguities, but Turkish and multilingual LLMs exhibit weak, unstable, or reversed shifts under the same conditions.