From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chowdhury, Nafis, Haque, Moinul, Ahmed, Anika, Tasnim, Nazia, Shihab, Md. Istiak Hossain, Rahman, Sajjadur, Sadeque, Farig
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918166817406976
author Chowdhury, Nafis
Haque, Moinul
Ahmed, Anika
Tasnim, Nazia
Shihab, Md. Istiak Hossain
Rahman, Sajjadur
Sadeque, Farig
author_facet Chowdhury, Nafis
Haque, Moinul
Ahmed, Anika
Tasnim, Nazia
Shihab, Md. Istiak Hossain
Rahman, Sajjadur
Sadeque, Farig
contents Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have advanced cultural evaluation for LLMs, critical gaps remain in capturing the nuances of low-resource cultures. Our work addresses these limitations through a Bengali Language Cultural Knowledge (BLanCK) dataset including folk traditions, culinary arts, and regional dialects. Our investigation of several multilingual language models shows that while these models perform well in non-cultural categories, they struggle significantly with cultural knowledge and performance improves substantially across all models when context is provided, emphasizing context-aware architectures and culturally curated training data.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
Chowdhury, Nafis
Haque, Moinul
Ahmed, Anika
Tasnim, Nazia
Shihab, Md. Istiak Hossain
Rahman, Sajjadur
Sadeque, Farig
Computation and Language
Machine Learning
I.2.7
Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have advanced cultural evaluation for LLMs, critical gaps remain in capturing the nuances of low-resource cultures. Our work addresses these limitations through a Bengali Language Cultural Knowledge (BLanCK) dataset including folk traditions, culinary arts, and regional dialects. Our investigation of several multilingual language models shows that while these models perform well in non-cultural categories, they struggle significantly with cultural knowledge and performance improves substantially across all models when context is provided, emphasizing context-aware architectures and culturally curated training data.
title From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
topic Computation and Language
Machine Learning
I.2.7
url https://arxiv.org/abs/2510.20043