# Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation

arXiv: https://arxiv.org/abs/2506.01565 · HTML: https://mlsanity.com/paper/2506.01565/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning](https://mlsanity.com/paper/2109.06860/) (2021)
- [CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries](https://mlsanity.com/paper/2501.01282/) (2025)
- [IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces](https://mlsanity.com/paper/2404.01854/) (2024)
- [WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines](https://mlsanity.com/paper/2410.12705/) (2024)
- [Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese](https://mlsanity.com/paper/2402.17302/) (2024)
- [An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance](https://mlsanity.com/paper/2404.01247/) (2024)
- [Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge](https://mlsanity.com/paper/2404.06833/) (2024)
- [M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks](https://mlsanity.com/paper/2407.03791/) (2024)
- [FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture](https://mlsanity.com/paper/2406.11030/) (2024)
- [Diffusion Models Through a Global Lens: Are They Culturally Inclusive?](https://mlsanity.com/paper/2502.08914/) (2025)
- [Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models](https://mlsanity.com/paper/2308.03151/) (2023)
- [An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage](https://mlsanity.com/paper/2501.02039/) (2025)
- [Towards Automatic Evaluation for Image Transcreation](https://mlsanity.com/paper/2412.13717/) (2024)
- [When Cultures Meet: Multicultural Text-to-Image Generation](https://mlsanity.com/paper/2502.15972/) (2025)
- [JEEM: Vision-Language Understanding in Four Arabic Dialects](https://mlsanity.com/paper/2503.21910/) (2025)
- [TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs](https://mlsanity.com/paper/2505.11275/) (2025)
- [Exploring LLM-Powered Role and Action-Switching Pedagogical Agents for History Education in Virtual Reality](https://mlsanity.com/paper/2505.02699/) (2025)

## Built on by (most cited first, 5 of 5)

- [Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses](https://mlsanity.com/paper/2601.13024/) (2026)
- [CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains](https://mlsanity.com/paper/2603.28474/) (2026)
- [Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics](https://mlsanity.com/paper/2605.27296/) (2026)
- [VietFashion: Benchmarking Sketch-Text Composed Image Retrieval for Cultural Outfits](https://mlsanity.com/paper/2606.13427/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

Culture is a rich and dynamic domain that evolves across both geography and time. However, existing studies on cultural understanding with vision-language models (VLMs) primarily emphasize geographic diversity, often overlooking the critical temporal dimensions. To bridge this gap, we introduce Hanfu-Bench, a novel, expert-curated multimodal dataset. Hanfu, a traditional garment spanning ancient Chinese dynasties, serves as a representative cultural heritage that reflects the profound temporal aspects of Chinese culture while remaining highly popular in Chinese contemporary society. Hanfu-Bench comprises two core tasks: cultural visual understanding and cultural image transcreation. The former task examines temporal-cultural feature recognition based on single- or multi-image inputs through multiple-choice visual question answering, while the latter focuses on transforming traditional attire into modern designs through cultural element inheritance and modern context adaptation. Our evaluation shows that closed VLMs perform comparably to non-experts on visual cutural understanding but fall short by 10% to human experts, while open VLMs lags further behind non-experts. For the transcreation task, multi-faceted human evaluation indicates that the best-performing model achieves a success rate of only 42%. Our benchmark provides an essential testbed, revealing significant challenges in this new direction of temporal cultural understanding and creative adaptation.