Suvach -- Generated Hindi QA benchmark
This provides a more accurate evaluation tool for Hindi NLP research, though it is incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of biased and inaccurate evaluation benchmarks for Hindi question answering by proposing a new benchmark generated using large language models, resulting in a high-quality dataset for extractive QA.
Current evaluation benchmarks for question answering (QA) in Indic languages often rely on machine translation of existing English datasets. This approach suffers from bias and inaccuracies inherent in machine translation, leading to datasets that may not reflect the true capabilities of EQA models for Indic languages. This paper proposes a new benchmark specifically designed for evaluating Hindi EQA models and discusses the methodology to do the same for any task. This method leverages large language models (LLMs) to generate a high-quality dataset in an extractive setting, ensuring its relevance for the target language. We believe this new resource will foster advancements in Hindi NLP research by providing a more accurate and reliable evaluation tool.