From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
This addresses a gap in capturing nuances for low-resource cultures like Bengali, which is incremental as it builds on existing multilingual benchmarks.
The paper tackled the problem of evaluating large language models on Bengali cultural knowledge, finding that while models perform well on non-cultural categories, they struggle significantly with cultural knowledge, with performance improving substantially when context is provided.
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.