BLUCK: A Benchmark Dataset for Bengali Linguistic Understanding and Cultural Knowledge
This work addresses the need for better evaluation benchmarks for Bengali language and culture in AI, though it is incremental as it primarily introduces a new dataset without novel methods.
The authors introduced BLUCK, a dataset of 2366 multiple-choice questions to evaluate Large Language Models on Bengali linguistic understanding and cultural knowledge, finding that models like GPT-4o and Claude-3.5-Sonnet perform reasonably overall but struggle in areas like Bengali phonetics, with Bengali identified as a mid-resource language.
In this work, we introduce BLUCK, a new dataset designed to measure the performance of Large Language Models (LLMs) in Bengali linguistic understanding and cultural knowledge. Our dataset comprises 2366 multiple-choice questions (MCQs) carefully curated from compiled collections of several college and job level examinations and spans 23 categories covering knowledge on Bangladesh's culture and history and Bengali linguistics. We benchmarked BLUCK using 6 proprietary and 3 open-source LLMs - including GPT-4o, Claude-3.5-Sonnet, Gemini-1.5-Pro, Llama-3.3-70B-Instruct, and DeepSeekV3. Our results show that while these models perform reasonably well overall, they, however, struggles in some areas of Bengali phonetics. Although current LLMs' performance on Bengali cultural and linguistic contexts is still not comparable to that of mainstream languages like English, our results indicate Bengali's status as a mid-resource language. Importantly, BLUCK is also the first MCQ-based evaluation benchmark that is centered around native Bengali culture, history, and linguistics.