# ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs

arXiv: https://arxiv.org/abs/2604.06484 · HTML: https://mlsanity.com/paper/2604.06484/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [BLINK: Multimodal Large Language Models Can See but Not Perceive](https://mlsanity.com/paper/2404.12390/) (2024)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)
- [GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition](https://mlsanity.com/paper/2301.02560/) (2023)
- [MIBench: Evaluating Multimodal Large Language Models over Multiple Images](https://mlsanity.com/paper/2407.15272/) (2024)
- [Assessment of Multimodal Large Language Models in Alignment with Human Values](https://mlsanity.com/paper/2403.17830/) (2024)
- [Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance](https://mlsanity.com/paper/2411.14279/) (2024)
- [Self-Pluralising Culture Alignment for Large Language Models](https://mlsanity.com/paper/2410.12971/) (2024)
- [OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference](https://mlsanity.com/paper/2502.18411/) (2025)
- [GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking](https://mlsanity.com/paper/2502.13766/) (2025)
- [Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models](https://mlsanity.com/paper/2502.14906/) (2025)
- [Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning](https://mlsanity.com/paper/2510.19733/) (2025)

## Built on by (most cited first, 1 of 1)

- [Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia](https://mlsanity.com/paper/2608.23065/) (2026)

## Abstract (arXiv)

Cultural values are expressed not only through language but also through visual scenes and everyday social practices. Yet existing evaluations of cultural values in language models are almost entirely text-only, leaving it unclear whether culture-conditioned judgments remain stable when response options are visualized. We introduce ValueGround, a benchmark for evaluating culture-conditioned visual value grounding in multimodal large language models (MLLMs). Built from World Values Survey questions, ValueGround uses minimally contrastive image pairs to represent opposing response options while controlling irrelevant variation. Given a country, a question, and an image pair, a model must choose the image that best matches the country's value tendency without access to the original response-option texts. Experiments across six MLLMs and 13 countries show that models perform substantially worse with visualized response options than with the original textual options, with average accuracy dropping from 72.8% to 62.6%. Our benchmark provides a controlled testbed for studying cross-modal transfer of culture-conditioned value judgments.