# Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration

arXiv: https://arxiv.org/abs/2406.16469 · HTML: https://mlsanity.com/paper/2406.16469/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [Aligning Large Language Models through Synthetic Feedback](https://mlsanity.com/paper/2305.13735/) (2023)
- [CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean](https://mlsanity.com/paper/2403.06412/) (2024)
- [Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning](https://mlsanity.com/paper/2109.06860/) (2021)
- [HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution](https://mlsanity.com/paper/2307.16883/) (2023)
- [GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition](https://mlsanity.com/paper/2301.02560/) (2023)
- [COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances](https://mlsanity.com/paper/2311.01012/) (2023)
- [Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants](https://mlsanity.com/paper/2112.09062/) (2021)
- [GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods](https://mlsanity.com/paper/2301.01893/) (2023)
- [Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond](https://mlsanity.com/paper/2310.14670/) (2023)

## Built on by (most cited first, 19 of 19)

- [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)
- [Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models](https://mlsanity.com/paper/2502.14906/) (2025)
- [Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought](https://mlsanity.com/paper/2510.04230/) (2025)
- [Seeing Culture: A Benchmark for Visual Reasoning and Grounding](https://mlsanity.com/paper/2509.16517/) (2025)
- [Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset](https://mlsanity.com/paper/2505.21979/) (2025)
- [KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts](https://mlsanity.com/paper/2508.19944/) (2025)
- [VARCO-VISION-2.0 Technical Report](https://mlsanity.com/paper/2509.10105/) (2025)
- [TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs](https://mlsanity.com/paper/2505.11275/) (2025)
- [When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts](https://mlsanity.com/paper/2503.16826/) (2025)
- [Evaluation of Cultural Competence of Vision-Language Models](https://mlsanity.com/paper/2505.22793/) (2025)
- [What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models](https://mlsanity.com/paper/2601.06165/) (2026)
- [The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation](https://mlsanity.com/paper/2602.11318/) (2026)
- [KorMedMCQA-V: A Multimodal Benchmark for Evaluating Vision-Language Models on the Korean Medical Licensing Examination](https://mlsanity.com/paper/2602.13650/) (2026)
- [EXAONE 4.5 Technical Report](https://mlsanity.com/paper/2604.08644/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)
- [PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding](https://mlsanity.com/paper/2608.21853/) (2026)
- [Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia](https://mlsanity.com/paper/2608.23065/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)

## Abstract (arXiv)

To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process labor-intensive and creating a cognitive burden in generating diverse questions. To address this, we propose a semi-automated framework for constructing cultural VLM benchmarks, specifically targeting multiple-choice QA. This framework combines human-VLM collaboration, where VLMs generate questions based on guidelines, a small set of annotated examples, and relevant knowledge, followed by a verification process by native speakers. We demonstrate the effectiveness of this framework through the creation of textttK-Viscuit, a dataset focused on Korean culture. Our experiments on this dataset reveal that open-source models lag behind proprietary ones in understanding Korean culture, highlighting key areas for improvement. We also present a series of further analyses, including human evaluation, augmenting VLMs with external knowledge, and the evaluation beyond multiple-choice QA. Our dataset is available at https://huggingface.co/datasets/ddehun/k-viscuit.