cs.CVNov 3, 2026

Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation

Authors: Zucan Lyu, Binwei Yao, Rheeya Uppaal, Jing Yao, Xiaoyuan Yi, Junjie Hu

Organizations: University of Wisconsin–Madison · Microsoft Research Asia

Abstract

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To bridge this gap, we introduce VisionValueBench, a multilingual benchmark that operationalizes six of Hofstede's cultural value dimensions (e.g., individualism versus collectivism) to investigate how T2I systems frame neutral social situations through a particular cultural orientation. We find that value-neutral prompts, which admit diverse cultural interpretations, nonetheless yield images that favor particular value orientations, a phenomenon we call visual value leakage. We evaluate prompts varying in language and geographic cues across 960 social scenarios and six T2I configurations. Generated images consistently favor the same value orientations across all six dimensions, for example, equality over hierarchy (low power distance), individual autonomy over group obligation (individualism), and enjoyment over restraint (indulgence). Prompt language has limited influence on these orientations, whereas geographic cues shift some dimensions toward the associated cultural values while largely preserving the prevailing orientations. These findings reveal substantial homogeneity in the cultural values conveyed by T2I systems worldwide.

Figures & tables

Appendix figures & tables29 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems

    Sep 10, 2026Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua +7T2I GenerationCultural Bias in Language Models

  2. CuRSE-Bench: A Benchmark for Probing Cultural Blind Spots in Text-to-Image Safety Evaluation

    Nov 16, 2026Minsuk Jang, Minseok Son, KiHyun Seol +2Cultural Safety Evaluation of VLMsT2I Generation Evaluation

  3. Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

    Jul 17, 2026Bo-An Chang, Yu-Chih ChenVLM EvaluationReward Modeling