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

• URL: http://arxiv.org/abs/2507.11049v2
• Date: Wed, 16 Jul 2025 03:58:24 GMT
• Title: Journalism-Guided Agentic In-Context Learning for News Stance Detection
• Authors: Dahyun Lee, Jonghyeon Choi, Jiyoung Han, Kunwoo Park,
• Abstract summary: Stance detection can enable viewpoint-aware recommendations and data-driven analyses of media bias.<n>We introduce textscK-News-Stance, the first Korean dataset for article-level stance detection.<n>We also propose textscJoA-ICL, a textbfJournalism-guided textbfAgentic textbfIn-textbfContext textbfL framework.
• Score: 1.6427963071264324
• License: http://creativecommons.org/licenses/by/4.0/
• 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 \textsc{K-News-Stance}, the first Korean dataset for article-level stance detection, comprising 2,000 news articles with article-level and 19,650 segment-level stance annotations across 47 societal issues. We also propose \textsc{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 show that \textsc{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.

Related papers

• Decoding News Bias: Multi Bias Detection in News Articles [1.433758865948252]
  We have explored various biases present in the news articles and built a dataset using large language models (LLMs)<n>Our approach highlights the importance of broad-spectrum bias detection and offers new insights for improving the integrity of news articles.
  arXiv  Detail & Related papers  (2025-01-05T09:09:53Z)
• VilBias: A Study of Bias Detection through Linguistic and Visual Cues , presenting Annotation Strategies, Evaluation, and Key Challenges [2.2751168722976587]
  VLBias is a framework that leverages state-of-the-art Large Language Models (LLMs) and Vision-Language Models (VLMs) to detect linguistic and visual biases in news content.<n>We present a multimodal dataset comprising textual content and corresponding images from diverse news sources.
  arXiv  Detail & Related papers  (2024-12-22T15:05:30Z)
• Understanding Cross-Lingual Alignment -- A Survey [52.572071017877704]
  Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models. We survey the literature of techniques to improve cross-lingual alignment, providing a taxonomy of methods and summarising insights from throughout the field.
  arXiv  Detail & Related papers  (2024-04-09T11:39:53Z)
• P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models [57.571395694391654]
  We find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries. We propose P3SUM, a diffusion model-based summarization approach controlled by political perspective classifiers. Experiments on three news summarization datasets demonstrate that P3SUM outperforms state-of-the-art summarization systems.
  arXiv  Detail & Related papers  (2023-11-16T10:14:28Z)
• Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection [50.07850264495737]
  "Prompt-and-Align" (P&A) is a novel prompt-based paradigm for few-shot fake news detection. We show that P&A sets new states-of-the-art for few-shot fake news detection performance by significant margins.
  arXiv  Detail & Related papers  (2023-09-28T13:19:43Z)
• X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs [55.80189506270598]
  X-PARADE is the first cross-lingual dataset of paragraph-level information divergences. Annotators label a paragraph in a target language at the span level and evaluate it with respect to a corresponding paragraph in a source language. Aligned paragraphs are sourced from Wikipedia pages in different languages.
  arXiv  Detail & Related papers  (2023-09-16T04:34:55Z)
• Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Start [65.28355014154549]
  This paper investigates the challenges of building scalable NLP systems for discovering patterns of media selection biases directly from news content in massive-scale news corpora. We show the capabilities of the framework through a case study on NELA-2020, a corpus of 1.8M news articles in English from 519 news sources worldwide.
  arXiv  Detail & Related papers  (2023-04-06T23:36:45Z)
• Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy [8.919312558800573]
  We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy.
  arXiv  Detail & Related papers  (2023-04-05T06:35:41Z)
• VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscripts [26.09365732823049]
  We propose a Visually Guided Text Spotting (VGTS) approach that accurately spots novel characters using just one annotated support sample. The DSA block aims to identify, focus on, and learn discriminative spatial regions in the support and query images, mimicking the human visual spotting process. To tackle the example imbalance problem in low-resource spotting tasks, we develop a novel torus loss function that enhances the discriminative power of the embedding space for distance metric learning.
  arXiv  Detail & Related papers  (2023-04-03T06:40:52Z)
• Contextual information integration for stance detection via cross-attention [59.662413798388485]
  Stance detection deals with identifying an author's stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information. We propose an approach to integrate contextual information as text.
  arXiv  Detail & Related papers  (2022-11-03T15:04:29Z)
• KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media [28.813287482918344]
  We propose KCD, a political perspective detection approach to enable multi-hop knowledge reasoning. Specifically, we generate random walks on external knowledge graphs and infuse them with news text representations. We then construct a heterogeneous information network to jointly model news content as well as semantic, syntactic and entity cues in news articles.
  arXiv  Detail & Related papers  (2022-04-08T13:06:09Z)
• Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding [71.2260967797055]
  We propose a weakly-supervised approach for aspect-based sentiment analysis. We learn sentiment, aspect> joint topic embeddings in the word embedding space. We then use neural models to generalize the word-level discriminative information.
  arXiv  Detail & Related papers  (2020-10-13T21:33:24Z)
• XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference [19.811371589597382]
  We study the problem of entity linking for Chinese news comments given mentions' spans. We propose a novel model, XREF, that leverages attention mechanisms to pinpoint relevant context. We develop a weakly supervised training scheme to utilize the large-scale unlabeled corpus.
  arXiv  Detail & Related papers  (2020-06-24T19:42:54Z)
• Generating Representative Headlines for News Stories [31.67864779497127]
  Grouping articles that are reporting the same event into news stories is a common way of assisting readers in their news consumption. It remains a challenging research problem to efficiently and effectively generate a representative headline for each story. We develop a distant supervision approach to train large-scale generation models without any human annotation.
  arXiv  Detail & Related papers  (2020-01-26T02:08:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.