When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908833448722432 |
|---|---|
| author | Sakhawat, Adib Parveen, Shamim Ara Amin, Md Ruhul Mahmud, Shamim Al Islam, Md Saiful Khatun, Tahera |
| author_facet | Sakhawat, Adib Parveen, Shamim Ara Amin, Md Ruhul Mahmud, Shamim Al Islam, Md Saiful Khatun, Tahera |
| contents | Figurative language understanding remains a significant challenge for Large Language Models (LLMs), especially for low-resource languages. To address this, we introduce a new idiom 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, 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, a stark contrast to significantly higher human performance (83.4%). This underscores the limitations of existing models in cross-linguistic and cultural reasoning. By releasing the new idiom dataset and benchmark, we provide foundational infrastructure for advancing figurative language understanding and cultural grounding in LLMs for Bengali and other low-resource languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12921 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms Sakhawat, Adib Parveen, Shamim Ara Amin, Md Ruhul Mahmud, Shamim Al Islam, Md Saiful Khatun, Tahera Computation and Language Figurative language understanding remains a significant challenge for Large Language Models (LLMs), especially for low-resource languages. To address this, we introduce a new idiom 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, 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, a stark contrast to significantly higher human performance (83.4%). This underscores the limitations of existing models in cross-linguistic and cultural reasoning. By releasing the new idiom dataset and benchmark, we provide foundational infrastructure for advancing figurative language understanding and cultural grounding in LLMs for Bengali and other low-resource languages. |
| title | When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.12921 |