Journalism-Guided Agentic In-context Learning for News Stance Detection

ACL ARR 2025 May Submission2509 Authors

Abstract: Understanding the overall stance of news articles is challenging due to their length and structural complexity. Yet, it is essential for supporting pluralistic and credible media environments. This paper introduces a novel stance detection dataset for Korean news, featuring annotations at both the article level and the segment level, informed by the narrative structure of news articles. Building on this resource, we propose an agentic in-context learning method that prompts a large language model (LLM) with segment-level stance predictions generated by a language model agent. Experiments across multiple LLMs demonstrate the effectiveness of the proposed framework for article-level stance detection and highlight its broader utility in enhancing diverse news recommendations and analyzing patterns of media bias.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: stance detection, news analysis, large language models, in-context learning

Contribution Types: NLP engineering experiment, Data resources, Data analysis

Languages Studied: Korean

Submission Number: 2509