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

arXiv: https://arxiv.org/abs/2602.12921 · HTML: https://mlsanity.com/paper/2602.12921/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [FLUTE: Figurative Language Understanding through Textual Explanations](https://mlsanity.com/paper/2205.12404/) (2022)
- [LIDIOMS: A Multilingual Linked Idioms Data Set](https://mlsanity.com/paper/1802.08148/) (2018)
- [Comparative Study of Multilingual Idioms and Similes in Large Language Models](https://mlsanity.com/paper/2410.16461/) (2024)
- [Computational historical linguistics and language diversity in South Asia](https://mlsanity.com/paper/2203.12524/) (2022)
- [A Survey of Idiom Datasets for Psycholinguistic and Computational Research](https://mlsanity.com/paper/2508.11828/) (2025)
- [Identifying Bengali Multiword Expressions using Semantic Clustering](https://mlsanity.com/paper/1401.6122/) (2014)

## Built on by (most cited first, 2 of 2)

- [Cross-Lingual Steering for Figurative Language Generation](https://mlsanity.com/paper/2605.30443/) (2026)
- [To What Extent Do Large Language Models Understand Bangla Idioms?](https://mlsanity.com/paper/2609.03410/) (2026)

## Abstract (arXiv)

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.