Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models

• URL: http://arxiv.org/abs/2602.02510v1
• Date: Fri, 23 Jan 2026 01:04:58 GMT
• Title: Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models
• Abstract summary: Cross-cultural meme transcreation is a task that aims to preserve communicative intent and humor while adapting culture-specific references.<n>We propose a hybrid transcreation framework based on vision-language models and introduce a large-scale bidirectional dataset of Chinese and US memes.
• Score: 9.43501626015691
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Memes are a pervasive form of online communication, yet their cultural specificity poses significant challenges for cross-cultural adaptation. We study cross-cultural meme transcreation, a multimodal generation task that aims to preserve communicative intent and humor while adapting culture-specific references. We propose a hybrid transcreation framework based on vision-language models and introduce a large-scale bidirectional dataset of Chinese and US memes. Using both human judgments and automated evaluation, we analyze 6,315 meme pairs and assess transcreation quality across cultural directions. Our results show that current vision-language models can perform cross-cultural meme transcreation to a limited extent, but exhibit clear directional asymmetries: US-Chinese transcreation consistently achieves higher quality than Chinese-US. We further identify which aspects of humor and visual-textual design transfer across cultures and which remain challenging, and propose an evaluation framework for assessing cross-cultural multimodal generation. Our code and dataset are publicly available at https://github.com/AIM-SCU/MemeXGen.

Related papers

• MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation [16.37143301773968]
  We introduce MemeBridge, a curated dataset centered on U.S.-originated memes.<n>Here, context refers to implicit cultural knowledge, including background beliefs, norms, and shared assumptions that shape meme comprehension.<n>We observe that the anticipated misunderstandings from U.S. participants are often inaccurate.
  arXiv  Detail & Related papers  (2026-08-31T23:38:23Z)
• TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation [13.601301289701892]
  Cross-cultural meme transcreation must preserve communicative intent, adapt culture-dependent meaning for the target audience, and maintain coherence between text and image.<n>We propose a multi-agent framework with specialized agents that are coordinated to address these challenges through cultural adaptation, target text rewriting, revision, and conditional visual adjustment.
  arXiv  Detail & Related papers  (2026-08-27T13:40:11Z)
• MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation [7.901765633133679]
  MAVEN is a multi-agent prompt refinement framework.<n>It decomposes prompts into person, action, and location dimensions.<n>It improves cultural fidelity in both mono-cultural and cross-cultural T2V generation.
  arXiv  Detail & Related papers  (2026-05-16T00:01:18Z)
• From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection [13.900106805972]
  We introduce a systematic evaluation framework designed to quantify the cross-cultural robustness of state-of-the-art vision-language models (VLMs)<n>We analyze three axes: (i) learning strategy (zero-shot vs. one-shot), (ii) prompting language (native vs. English), and (iii) translation effects on meaning and detection.<n>Results show that the common translate-then-detect'' approach deteriorates performance, while culturally aligned interventions - native-language prompting and one-shot learning - significantly enhance detection.
  arXiv  Detail & Related papers  (2026-02-07T11:14:57Z)
• Do Large Language Models Truly Understand Cross-cultural Differences? [53.481048019144644]
  We develop a scenario-based benchmark to evaluate large language models' cross-cultural understanding and reasoning.<n>Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions.<n>The dataset supports continuous expansion, and experiments confirm its transferability to other languages.
  arXiv  Detail & Related papers  (2025-12-08T01:21:58Z)
• Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation [43.352493955825736]
  We show that current T2I models often produce culturally neutral or English-biased results under multilingual prompts.<n>We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers.
  arXiv  Detail & Related papers  (2025-11-21T14:40:50Z)
• MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation [91.22008265721952]
  MMA-ASIA centers on a human-curated, multilingual, and multimodally aligned benchmark covering 8 Asian countries and 10 languages.<n>This is the first dataset aligned at the input level across three modalities: text, image (visual question answering), and speech.<n>We propose a five-dimensional evaluation protocol that measures: (i) cultural-awareness disparities across countries, (ii) cross-lingual consistency, (iii) cross-modal consistency, (iv) cultural knowledge generalization, and (v) grounding validity.
  arXiv  Detail & Related papers  (2025-10-07T14:12:12Z)
• Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation [2.0467354053171243]
  We present the first comprehensive evaluation of Vision-Language Models (VLMs) cultural competence through multimodal story generation.<n>Our analysis reveals significant cultural adaptation capabilities, with rich culturally-specific vocabulary spanning names, familial terms, and geographic markers.<n>We uncover concerning limitations: cultural competence varies dramatically across architectures, some models exhibit inverse cultural alignment, and automated metrics show architectural bias contradicting human assessments.
  arXiv  Detail & Related papers  (2025-08-22T19:39:02Z)
• CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation [47.54347964192231]
  We introduce CaMMT, a benchmark of over 5,800 triples of images along with parallel captions in English and regional languages.<n>Through automatic and human evaluations, we find that visual context generally improves translation quality.
  arXiv  Detail & Related papers  (2025-05-30T10:42:44Z)
• TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs [13.069833806549914]
  We propose the Traditional Chinese Culture understanding Benchmark (TCC-Bench) for assessing the understanding of traditional Chinese culture.<n>TCC-Bench comprises culturally rich and visually diverse data, incorporating images from museum artifacts, everyday life scenes, comics, and other culturally significant contexts.<n>We adopt a semi-automated pipeline that utilizes GPT-4o in text-only mode to generate candidate questions, followed by human curation to ensure data quality and avoid potential data leakage.
  arXiv  Detail & Related papers  (2025-05-16T14:10:41Z)
• CulturePark: Boosting Cross-cultural Understanding in Large Language Models [63.452948673344395]
  This paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. We evaluate these models across three downstream tasks: content moderation, cultural alignment, and cultural education.
  arXiv  Detail & Related papers  (2024-05-24T01:49:02Z)
• CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models [59.22460740026037]
  "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset is designed to evaluate the social and cultural variation of Large Language Models (LLMs) We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy.
  arXiv  Detail & Related papers  (2024-05-22T20:19:10Z)
• On the Cultural Gap in Text-to-Image Generation [75.69755281031951]
  One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data. There is no benchmark to systematically evaluate a T2I model's ability to generate cross-cultural images. We propose a Challenging Cross-Cultural (C3) benchmark with comprehensive evaluation criteria, which can assess how well-suited a model is to a target culture.
  arXiv  Detail & Related papers  (2023-07-06T13:17:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.