TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation

• URL: http://arxiv.org/abs/2608.27127v1
• Date: Thu, 27 Aug 2026 13:40:11 GMT
• Title: TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation
• Abstract summary: 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.
• Score: 13.601301289701892
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Internet memes are a pervasive form of multimodal online communication; however, such communication often involves users from diverse linguistic and cultural backgrounds. Therefore, adapting memes across cultures and languages is a central challenge for enabling mutual understanding in online communication. Unlike ordinary translation or standalone text rewriting, cross-cultural meme transcreation must jointly preserve communicative intent, adapt culture-dependent meaning for the target audience, and maintain coherence between text and image. In this work, we first provide an explicit task analysis of cross-cultural meme transcreation and identify three core challenges: culture-specific knowledge understanding, intent and tone preservation, and multimodal consistency. Based on this analysis, 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. The framework strengthens target text adaptation with coordinated feedback to handle difficult cases that require deeper cultural or visual intervention. We evaluate the framework on bidirectional Chinese-English meme transcreation using both human evaluation and LLM-as-a-Judge. Our method consistently outperforms all baselines across both evaluation settings. In human evaluation, it achieves the best performance on all four dimensions and delivers a 33.1% average improvement over the strongest baseline, while in LLM-as-a-Judge, it attains the highest Top-1 ranking rate (60% versus 26% for the second-best baseline). Further analysis indicates that each component contributes to the performance. Our error analysis suggests that the remaining bottlenecks lie in humor reconstruction and image-text alignment rather than simple cultural knowledge gaps, pointing to future work on humor transfer.

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)
• 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)
• Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models [9.43501626015691]
  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.
  arXiv  Detail & Related papers  (2026-01-23T01:04:58Z)
• 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)
• CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs [57.653830744706305]
  CultureScope is the most comprehensive evaluation framework to date for assessing cultural understanding in large language models.<n>Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification.<n> Experimental results demonstrate that our method can effectively evaluate cultural understanding.
  arXiv  Detail & Related papers  (2025-09-19T17:47:48Z)
• 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)
• CAReDiO: Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization [50.90288681622152]
  Large Language Models (LLMs) more deeply integrate into human life across various regions.<n>Existing approaches develop culturally aligned LLMs through fine-tuning with culture-specific corpora.<n>We introduce CAReDiO, a novel cultural data construction framework.
  arXiv  Detail & Related papers  (2025-04-09T13:40:13Z)
• Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking [48.21982147529661]
  This paper introduces a novel approach for massively multicultural knowledge acquisition. Our method strategically navigates from densely informative Wikipedia documents on cultural topics to an extensive network of linked pages. Our work marks an important step towards deeper understanding and bridging the gaps of cultural disparities in AI.
  arXiv  Detail & Related papers  (2024-02-14T18:16:54Z)
• Benchmarking Machine Translation with Cultural Awareness [50.183458829028226]
  Translating culture-related content is vital for effective cross-cultural communication. Many culture-specific items (CSIs) often lack viable translations across languages. This difficulty hinders the analysis of cultural awareness of machine translation systems.
  arXiv  Detail & Related papers  (2023-05-23T17:56:33Z)

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.