A computational audit examining how LLMs handle metaphors and cultural translation. The paper investigates whether models perform genuine cultural understanding or rely on surface-level pattern matching when processing metaphorical language.
Research
Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs
A computational audit finds that LLMs pattern-match rather than truly understand cultural metaphors, suggesting surface-level linguistic facility masks deeper gaps in cultural reasoning.
Tuesday, April 7, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.CL (Computation & Language)BY sys://pipeline
Tags
research