Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs

Yuan Chang, Jiaming Qu, Zhu Li

Abstract

Large language models (LLMs) are often described as multilingual because they can understand and respond in many languages. However, speaking a language is not the same as reasoning within a culture. This distinction motivates a critical question: do LLMs truly conduct culture-aware reasoning? This paper presents a preliminary computational audit of cultural inclusivity in a creative writing task. We empirically examine whether LLMs act as culturally diverse creative partners or merely as cultural translators that leverage a dominant conceptual framework with localized expressions. Using a metaphor generation task spanning five cultural settings and several abstract concepts as a case study, we find that the model exhibits stereotyped metaphor usage for certain settings, as well as Western defaultism. These findings suggest that merely prompting an LLM with a cultural identity does not guarantee culturally grounded reasoning.

Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs

Abstract

Large language models (LLMs) are often described as multilingual because they can understand and respond in many languages. However, speaking a language is not the same as reasoning within a culture. This distinction motivates a critical question: do LLMs truly conduct culture-aware reasoning? This paper presents a preliminary computational audit of cultural inclusivity in a creative writing task. We empirically examine whether LLMs act as culturally diverse creative partners or merely as cultural translators that leverage a dominant conceptual framework with localized expressions. Using a metaphor generation task spanning five cultural settings and several abstract concepts as a case study, we find that the model exhibits stereotyped metaphor usage for certain settings, as well as Western defaultism. These findings suggest that merely prompting an LLM with a cultural identity does not guarantee culturally grounded reasoning.

Paper Structure

This paper contains 14 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Task Overview
  4. Metaphor Generation
  5. Evaluations
  6. Results
  7. Analysis I: Intra-Cultural Diversity
  8. Analysis II: Conceptual Geometry
  9. Analysis III: Western Defaultism
  10. Qualitative Analysis of Metaphors
  11. Discussion and Conclusion
  12. Summary of Findings
  13. Implications for Co-Creative Use of LLMs
  14. Limitations and Future Work

Figures (2)

  • Figure 1: Intra-cultural semantic diversity of metaphors. Each cell shows the average pairwise cosine distance among 20 generated metaphors for a given (concept, culture) pair. Higher values indicate greater semantic diversity, while lower values indicate representational collapse.
  • Figure 2: Conceptual geometry of metaphor embeddings across cultures. Each panel shows a t-SNE projection of metaphor embeddings for one cultural condition. Colors indicate distinct abstract concepts.