KOBEST: Korean Balanced Evaluation of Significant Tasks
This addresses the problem of limited evaluation resources for Korean NLP, though it is incremental as it adapts benchmark concepts to a low-resource language.
The authors tackled the lack of Korean-language benchmarks for evaluating language models by creating KoBEST, a benchmark with five tasks requiring advanced Korean linguistic knowledge, achieving human-annotated high-quality data with baseline models and human performance results.
A well-formulated benchmark plays a critical role in spurring advancements in the natural language processing (NLP) field, as it allows objective and precise evaluation of diverse models. As modern language models (LMs) have become more elaborate and sophisticated, more difficult benchmarks that require linguistic knowledge and reasoning have been proposed. However, most of these benchmarks only support English, and great effort is necessary to construct benchmarks for other low resource languages. To this end, we propose a new benchmark named Korean balanced evaluation of significant tasks (KoBEST), which consists of five Korean-language downstream tasks. Professional Korean linguists designed the tasks that require advanced Korean linguistic knowledge. Moreover, our data is purely annotated by humans and thoroughly reviewed to guarantee high data quality. We also provide baseline models and human performance results. Our dataset is available on the Huggingface.