Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory

TL;DR

This paper introduces a three-level taxonomy of AI cultural capabilities based on intercultural communication theory to improve evaluation clarity and effectiveness in multicultural settings.

Contribution

It provides a novel, grounded taxonomy to clarify and standardize the evaluation of AI cultural capabilities, addressing construct ambiguity.

Findings

Proposes a three-level taxonomy: Awareness, Sensitivity, Competence.

Highlights risks of ambiguous cultural capability definitions in AI evaluation.

Offers a practical tool for more valid and interpretable multicultural AI assessments.

Abstract

Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using interchangeable terminology, and are typically limited to recalling accurate information about various demographics, regions, and nationalities. To address this construct ambiguity, we draw from Intercultural Communication scholarship and propose a three-level taxonomy of AI-relevant cultural capabilities: Cultural Awareness answers "Does the model know?", Cultural Sensitivity answers "How does it frame its knowledge?", and Cultural Competence answers "Can it adapt as the interaction evolves?". Beyond conceptual clarification, we position this taxonomy as a practical tool for improving the validity and interpretability of AI evaluation in real-world, multicultural settings. Without such construct clarity, evaluation results risk overstating model capabilities and may lead to inappropriate deployment decisions in culturally sensitive contexts.