Author

Donghyeon Ko

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Oct 2025

KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs

A comprehensive evaluation across a diverse set of open-source LLMs of varying sizes that support Korean finds that even the strongest model generates correct answer only 31.6% of the time, underscoring the challenging nature of KoSimpleQA.

Donghyeon Ko, Ye Jin, Kyubyung Chae et al. · arXiv.org · 1 citation