Request Correction

When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms

Figurative language understanding remains a significant challenge for Large Language Models (LLMs), especially for low-resource languages. To address this, we introduce the *Bangla Bagdhara* dataset, a large-scale, culturally grounded corpus of 10,361 Bengali idioms. Each idiom is annotated under a comprehensive 19-field schema, established and refined through a deliberative expert consensus process that captures its semantic, syntactic, cultural, and religious dimensions, providing a rich and structured resource for computational linguistics. To establish a robust benchmark for Bangla figurative language understanding, we evaluate 30 state-of-the-art multilingual and instruction-tuned LLMs on the task of inferring figurative meaning. Our results reveal a critical performance gap, with no model surpassing 50% accuracy, in stark contrast to significantly higher human performance (83.4%). This finding underscores the limitations of existing models in cross-linguistic and cultural reasoning. By releasing the *Bangla Bagdhara* dataset and benchmark, we provide foundational infrastructure for advancing figurative language understanding and cultural grounding in LLMs for Bengali and other low-resource languages.