# Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models

arXiv: https://arxiv.org/abs/2502.14906 · HTML: https://mlsanity.com/paper/2502.14906/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 73 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World](https://mlsanity.com/paper/1711.08536/) (2017)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)
- [Extracting Cultural Commonsense Knowledge at Scale](https://mlsanity.com/paper/2210.07763/) (2022)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [Knowledge of cultural moral norms in large language models](https://mlsanity.com/paper/2306.01857/) (2023)
- [COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances](https://mlsanity.com/paper/2311.01012/) (2023)
- [EtiCor: Corpus for Analyzing LLMs for Etiquettes](https://mlsanity.com/paper/2310.18974/) (2023)
- [This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models](https://mlsanity.com/paper/2305.14610/) (2023)
- [Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy](https://mlsanity.com/paper/2205.12771/) (2022)
- [Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration](https://mlsanity.com/paper/2406.16469/) (2024)
- [Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models](https://mlsanity.com/paper/2310.01929/) (2023)
- [Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing](https://mlsanity.com/paper/2402.06015/) (2024)
- [On the Cultural Gap in Text-to-Image Generation](https://mlsanity.com/paper/2307.02971/) (2023)
- [CIC: A Framework for Culturally-Aware Image Captioning](https://mlsanity.com/paper/2402.05374/) (2024)
- [CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation](https://mlsanity.com/paper/2407.01081/) (2024)
- [Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey](https://mlsanity.com/paper/2408.04643/) (2024)
- [The African Woman is Rhythmic and Soulful: An Investigation of Implicit Biases in LLM Open-ended Text Generation](https://mlsanity.com/paper/2407.01270/) (2024)

## Built on by (most cited first, 14 of 14)

- [DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture](https://mlsanity.com/paper/2509.19274/) (2025)
- [RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding](https://mlsanity.com/paper/2505.14462/) (2025)
- [Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies](https://mlsanity.com/paper/2505.14972/) (2025)
- [Uncovering Cultural Representation Disparities in Vision-Language Models](https://mlsanity.com/paper/2505.14729/) (2025)
- [Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations](https://mlsanity.com/paper/2511.05613/) (2025)
- [Evaluation of Cultural Competence of Vision-Language Models](https://mlsanity.com/paper/2505.22793/) (2025)
- [Finding Culture-Sensitive Neurons in Vision-Language Models](https://mlsanity.com/paper/2510.24942/) (2025)
- [World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models](https://mlsanity.com/paper/2511.22787/) (2025)
- [A Unified Framework to Quantify Cultural Intelligence of AI](https://mlsanity.com/paper/2603.01211/) (2026)
- [On The Conceptualization and Societal Impact of Cross-Cultural Bias](https://mlsanity.com/paper/2512.21809/) (2025)
- [From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme](https://mlsanity.com/paper/2512.24555/) (2025)
- [ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs](https://mlsanity.com/paper/2604.06484/) (2026)
- [Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation](https://mlsanity.com/paper/2604.02557/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Investigating value alignment in Large Language Models (LLMs) based on cultural context has become a critical area of research. However, similar biases have not been extensively explored in large vision-language models (VLMs). As the scale of multimodal models continues to grow, it becomes increasingly important to assess whether images can serve as reliable proxies for culture and how these values are embedded through the integration of both visual and textual data. In this paper, we conduct a thorough evaluation of multimodal model at different scales, focusing on their alignment with cultural values. Our findings reveal that, much like LLMs, VLMs exhibit sensitivity to cultural values, but their performance in aligning with these values is highly context-dependent. While VLMs show potential in improving value understanding through the use of images, this alignment varies significantly across contexts highlighting the complexities and underexplored challenges in the alignment of multimodal models.