Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation
Xinyu Wang, Sai Koneru, Wenbo Zhang, Wenliang Zheng, Saksham Ranjan + 1 more
TLDR
This paper introduces MANYFAKE, a new benchmark for detecting subtle, strategically generated fake news, revealing current models struggle with mixed-truth content.
Key contributions
- Introduces MANYFAKE, a 6,798-article benchmark for detecting subtle, strategy-driven fake news.
- Addresses the gap of "mixed-truth" fake news, where inaccuracies are embedded in credible narratives.
- Evaluates SOTA detectors, showing brittleness against subtle falsehoods, despite excelling at fully fabricated news.
Why it matters
Modern fake news often blends truth with strategic falsehoods, a challenge current detection methods and benchmarks overlook. This paper provides a crucial benchmark, MANYFAKE, to push research towards more robust detection of these sophisticated, human-AI generated deceptions.
Original Abstract
Recent advances in large language models (LLMs) have enabled the large-scale generation of highly fluent and deceptive news-like content. While prior work has often treated fake news detection as a binary classification problem, modern fake news increasingly arises through human-AI collaboration, where strategic inaccuracies are embedded within otherwise accurate and credible narratives. These mixed-truth cases represent a realistic and consequential threat, yet they remain underrepresented in existing benchmarks. To address this gap, we introduce MANYFAKE, a synthetic benchmark containing 6,798 fake news articles generated through multiple strategy-driven prompting pipelines that capture many ways fake news can be constructed and refined. Using this benchmark, we evaluate a range of state-of-the-art fake news detectors. Our results show that even advanced reasoning-enabled models approach saturation on fully fabricated stories, but remain brittle when falsehoods are subtle, optimized, and interwoven with accurate information.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.