humane-lab/klue-roberta-large-JoA-segment

JoA-ICL RoBERTa Segment Model

Paper | Code

Model Summary

This model is a segment model used in JoA-ICL to predict the stance of a segment toward an issue.

License

This model is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.

Citation

@inproceedings{lee-etal-2025-journalism,
    title = "Journalism-Guided Agentic In-context Learning for News Stance Detection",
    author = "Lee, Dahyun  and
      Choi, Jonghyeon  and
      Han, Jiyoung  and
      Park, Kunwoo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.778/",
    doi = "10.18653/v1/2025.emnlp-main.778",
    pages = "15404--15427",
    ISBN = "979-8-89176-332-6",
    abstract = "As online news consumption grows, personalized recommendation systems have become integral to digital journalism. However, these systems risk reinforcing filter bubbles and political polarization by failing to incorporate diverse perspectives. Stance detection{---}identifying a text{'}s position on a target{---}can help mitigate this by enabling viewpoint-aware recommendations and data-driven analyses of media bias. Yet, existing stance detection research remains largely limited to short texts and high-resource languages. To address these gaps, we introduce K-News-Stance, the first Korean dataset for article-level stance detection, comprising 2,000 news articles with article-level and 21,650 segment-level stance annotations across 47 societal issues. We also propose JoA-ICL, a \textbf{Jo}urnalism-guided \textbf{A}gentic \textbf{I}n-\textbf{C}ontext \textbf{L}earning framework that employs a language model agent to predict the stances of key structural segments (e.g., leads, quotes), which are then aggregated to infer the overall article stance. Experiments showed that JoA-ICL outperforms existing stance detection methods, highlighting the benefits of segment-level agency in capturing the overall position of long-form news articles. Two case studies further demonstrate its broader utility in promoting viewpoint diversity in news recommendations and uncovering patterns of media bias."
}