BEnQA: A Question Answering and Reasoning Benchmark for Bengali and English
This addresses the problem of evaluating and improving LLM performance for low-resource languages like Bengali, though it is incremental as it builds on existing multilingual QA benchmarks.
The authors introduced BEnQA, a parallel Bengali and English dataset of about 5K middle and high school science questions, and benchmarked LLMs, finding a notable performance disparity between languages and that Chain-of-Thought prompting helps reasoning questions but not factual ones.
In this study, we introduce BEnQA, a dataset comprising parallel Bengali and English exam questions for middle and high school levels in Bangladesh. Our dataset consists of approximately 5K questions covering several subjects in science with different types of questions, including factual, application, and reasoning-based questions. We benchmark several Large Language Models (LLMs) with our parallel dataset and observe a notable performance disparity between the models in Bengali and English. We also investigate some prompting methods, and find that Chain-of-Thought prompting is beneficial mostly on reasoning questions, but not so much on factual ones. We also find that appending English translation helps to answer questions in Bengali. Our findings point to promising future research directions for improving the performance of LLMs in Bengali and more generally in low-resource languages.