@inproceedings{jung-etal-2026-thunder,
    title = "Thunder-{K}o{NUB}ench: A Corpus-Aligned Benchmark for {K}orean Negation Understanding",
    author = "Jung, Sungmok  and
      So, Yeonkyoung  and
      Lee, Joonhak  and
      Kim, Sangho  and
      Ahn, Yelim  and
      Lee, Jaejin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.324/",
    pages = "6491--6518",
    ISBN = "979-8-89176-395-1",
    abstract = "Although negation is known to challenge large language models (LLMs), benchmarks for evaluating negation understanding{---}especially in Korean{---}are scarce. We conduct a corpus-based analysis of Korean negation and show that LLM performance degrades under negation. We then introduce *Thunder-KoNUBench*, a sentence-level negation understanding benchmark that reflects the empirical distribution of Korean negation phenomena. Evaluating 47 LLMs on Thunder-KoNUBench, we analyze the effects of model size and instruction tuning, and perform error analysis to better understand model behavior. We further show that fine-tuning on Thunder-KoNUBench improves negation understanding and broader contextual comprehension in Korean."
}