We present Ko-MuSR, the first benchmark to comprehensively evaluate multistep, soft reasoning in long Korean narratives while minimizing data contamination. Built following MuSR, Ko-MuSR features fully Korean narratives, reasoning chains, and multiple-choice questions verified by human annotators for logical consistency and answerability. Evaluations of four large language models -- two multilingual and two Korean-specialized -- show that multilingual models outperform Korean-focused ones even in Korean reasoning tasks, indicating cross-lingual generalization of reasoning ability. Carefully designed prompting strategies, which combine few-shot examples, reasoning traces, and task-specific hints, further boost accuracy, approaching human-level performance. Ko-MuSR offers a solid foundation for advancing Korean NLP by enabling systematic evaluation of long-context reasoning and prompting strategies.
@article{arxiv.2510.24150,
title = {Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean},
author = {Chanwoo Park and Suyoung Park and JiA Kang and Jongyeon Park and Sangho Kim and Hyunji M. Park and Sumin Bae and Mingyu Kang and Jaejin Lee},
journal= {arXiv preprint arXiv:2510.24150},
year = {2025}
}