mlsanityData to 7 Oct 2026

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

arXiv 2507.11049 ↗First posted 15 Jul 2025cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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 textscK-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 textscJoA-ICL, a Journalism-guided Agentic In-Context Learning framework that employs a language model agent to predict the stances of key structural segments (e.g., leads, quotations), which are then aggregated to infer the overall article stance. Experiments showed that textscJoA-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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 109 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

33 of 109 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  6. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  7. 2024In-Context Learning with Long-Context Models: An In-Depth Explorationcited by 126
  8. 2021KLUE: Korean Language Understanding Evaluationcited by 113
  9. 2016Stance Detection with Bidirectional Conditional Encodingcited by 93
  10. 2020Stance Detection on Social Media: State of the Art and Trendscited by 93
  11. 2020We Can Detect Your Bias: Predicting the Political Ideology of News Articlescited by 92
  12. 2023Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Taskscited by 88
21 more
  1. 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
  2. 2018Predicting Factuality of Reporting and Bias of News Media Sourcescited by 71
  3. 2023Stance Detection with Collaborative Role-Infused LLM-Based Agentscited by 53
  4. 2022POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detectioncited by 50
  5. 2024EXAONE 3.5: Series of Large Language Models for Real-world Use Casescited by 50
  6. 2019Unsupervised User Stance Detection on Twittercited by 45
  7. 2020Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularitycited by 32
  8. 2020Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Mediacited by 27
  9. 2020A Systematic Media Frame Analysis of 1.5 Million New York Times Articles from 2000 to 2017cited by 23
  10. 2022Infusing Knowledge from Wikipedia to Enhance Stance Detectioncited by 20
  11. 2023Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classificationcited by 16
  12. 2018Detecting Incongruity Between News Headline and Body Text via a Deep Hierarchical Encodercited by 15
  13. 2024IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicatorscited by 15
  14. 2023Automated stance detection in complex topics and small languages: the challenging case of immigration in polarizing news mediacited by 14
  15. 2023Chain-of-Thought Embeddings for Stance Detection on Social Mediacited by 13
  16. 2018Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake Newscited by 11
  17. 2024A Survey of Stance Detection on Social Media: New Directions and Perspectivescited by 8
  18. 2022Towards Analyzing the Bias of News Recommender Systems Using Sentiment and Stance Detectioncited by 7
  19. 2023Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchycited by 6
  20. 2024Echo Chambers in the Age of Algorithms: An Audit of Twitter's Friend Recommender Systemcited by 3
  21. 2023Detecting Contextomized Quotes in News Headlines by Contrastive Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Visual Framing for News Stance Detection via Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning
  2. 2025Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models
  3. 2026StanceMoE: Mixture-of-Experts Architecture for Stance Detection
  4. 2024Reasoner Outperforms: Generative Stance Detection with Rationalization for Social Media
  5. 2025Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability
  6. 2025MT2-CSD: A New Dataset and Multi-Semantic Knowledge Fusion Method for Conversational Stance Detection
  7. 2025Collaborative Stance Detection via Small-Large Language Model Consistency Verification
  8. 2026Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning