LLMs produce stereotyped and Western-biased metaphors in culturally prompted creative tasks, indicating they translate rather than reason within cultures.
InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (V olume 1: Long Papers), 18761–18799
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
-
Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs
LLMs produce stereotyped and Western-biased metaphors in culturally prompted creative tasks, indicating they translate rather than reason within cultures.