CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean

arXiv:2403.06412v1 Announce Type: new
Abstract: Despite the rapid development of large language models (LLMs) for the Korean language, there remains an obvious lack of benchmark datasets that test the requisite Korean cultural and linguistic knowledge. Because many existing Korean benchmark datasets are derived from the English counterparts through translation, they often overlook the different cultural contexts. For the few benchmark datasets that are sourced from Korean data capturing cultural knowledge, only narrow tasks such as bias and hate speech detection …

abstract arxiv benchmark click cs.cl dataset datasets development english intelligence knowledge language language models large language large language models llms test through translation type