Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats

2025-12-04

AI Summary

Local news is increasingly threatened by “pink slime journalism”—low-quality, automatically generated content masquerading as legitimate reporting. Large language models (LLMs) enable adversarial paraphrasing that significantly degrades the performance of existing pink slime detectors. This paper presents the first systematic analysis of how LLM-driven adversarial rewriting undermines detection, revealing underlying linguistic mechanisms through feature analysis and adversarial sample training. We propose a robust, adaptive detection framework integrating fine-grained stylistic modeling, transferable feature extraction, and an adversarially enhanced classifier. Experiments show that state-of-the-art detectors suffer up to a 40% drop in F1 score under LLM-based attacks; our framework not only fully recovers baseline performance but achieves up to a 27% absolute improvement, markedly strengthening resilience against generative disinformation.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The local news landscape, a vital source of reliable information for 28 million Americans, faces a growing threat from Pink Slime Journalism, a low-quality, auto-generated articles that mimic legitimate local reporting. Detecting these deceptive articles requires a fine-grained analysis of their linguistic, stylistic, and lexical characteristics. In this work, we conduct a comprehensive study to uncover the distinguishing patterns of Pink Slime content and propose detection strategies based on these insights. Beyond traditional generation methods, we highlight a new adversarial vector: modifications through large language models (LLMs). Our findings reveal that even consumer-accessible LLMs can significantly undermine existing detection systems, reducing their performance by up to 40% in F1-score. To counter this threat, we introduce a robust learning framework specifically designed to resist LLM-based adversarial attacks and adapt to the evolving landscape of automated pink slime journalism, and showed and improvement by up to 27%.

Problem

• Detecting low-quality auto-generated pink slime journalism articles
• Addressing adversarial threats from large language models to detection systems
• Developing a robust learning framework to resist LLM-based attacks

Innovation

• Linguistic analysis for detecting auto-generated journalism
• Framework to resist LLM-based adversarial attacks
• Adaptive detection for evolving automated journalism threats