BanglaMemeX: Advancing Cultural Metaphoric Image Interpretation in Bangla with a Multimodal Explainable Dataset

2026-09-07

AI Summary

本文通过构建包含3000个孟加拉语梗图的多模态数据集BanglaMemeX，旨在提升AI模型对文化隐喻图像的理解能力。

Abstract

Vision Language Models have achieved strong performance on multimodal benchmarks, yet their ability to reason about culturally grounded and metaphor-rich content remains insufficiently studied. Internet memes present a challenging setting where meaning emerges from implicit interactions between image, overlaid text, sarcasm, and shared socio-cultural knowledge rather than literal visual recognition. This challenge is amplified in low-resource languages such as Bangla, where code-mixing, stylized scripts, and culturally specific symbolism introduce substantial distribution shift. In this work, we introduce BanglaMemeX, a culturally grounded multimodal benchmark comprising 3,000 Bangla memes annotated with multi-dimensional labels (humor, sarcasm, offensiveness, motivational intent, and overall sentiment) and human-written explanations that explicitly describe textual and visual metaphors. We systematically evaluate modern VLMs on both classification and explanation generation, revealing that current models struggle to interpret implicit cultural cues despite reasonable surface-level accuracy. Our results highlight the need for culturally-aware multimodal systems capable of grounded reasoning under linguistic and cultural distribution shift.

Problem

• Culturally grounded
• multimodal data
• metaphoric content
• low-resource languages
• distribution shift

Innovation

• multimodal benchmark
• cultural metaphors
• explanation generation
• distribution shift