@inproceedings{yu-etal-2025-ground,
    title = "From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary {K}orean Political Discourse",
    author = "Yu, Seunguk  and
      Yun, JungMin  and
      Jang, Jinhee  and
      Kim, YoungBin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1199/",
    doi = "10.18653/v1/2025.findings-emnlp.1199",
    pages = "21994--22014",
    ISBN = "979-8-89176-335-7",
    abstract = "Although offensive language continually evolves over time, even recent studies using LLMs have predominantly relied on outdated datasets and rarely evaluated the generalization ability on unseen texts. In this study, we constructed a large-scale dataset of contemporary political discourse and employed three refined judgments in the absence of ground truth. Each judgment reflects a representative offensive language detection method and is carefully designed for optimal conditions. We identified distinct patterns for each judgment and demonstrated tendencies of label agreement using a leave-one-out strategy. By establishing pseudo-labels as ground trust for quantitative performance assessment, we observed that a strategically designed single prompting achieves comparable performance to more resource-intensive methods. This suggests a feasible approach applicable in real-world settings with inherent constraints."
}