Dual Perspectives in Emotion Attribution: A Generator-Interpreter Framework for Cross-Cultural Analysis of Emotion in LLMs

TL;DR

This paper introduces a dual-perspective framework for emotion attribution in LLMs, emphasizing cultural differences in expression and interpretation to improve cross-cultural emotion understanding.

Contribution

It proposes a generator-interpreter framework that considers both expression and interpretation, addressing cultural variability in emotion attribution by LLMs.

Findings

Performance varies with emotion type and cultural context.

Generator's country of origin significantly influences performance.

Alignment effects between generator and interpreter perspectives are observed.

Abstract

Large language models (LLMs) are increasingly used in cross-cultural systems to understand and adapt to human emotions, which are shaped by cultural norms of expression and interpretation. However, prior work on emotion attribution has focused mainly on interpretation, overlooking the cultural background of emotion generators. This assumption of universality neglects variation in how emotions are expressed and perceived across nations. To address this gap, we propose a Generator-Interpreter framework that captures dual perspectives of emotion attribution by considering both expression and interpretation. We systematically evaluate six LLMs on an emotion attribution task using data from 15 countries. Our analysis reveals that performance variations depend on the emotion type and cultural context. Generator-interpreter alignment effects are present; the generator's country of origin has a stronger impact on performance. We call for culturally sensitive emotion modeling in LLM-based systems to improve robustness and fairness in emotion understanding across diverse cultural contexts.