Many Ways to Be Fake: Benchmarking Fake News Detection Under Strategy-Driven AI Generation
This addresses the realistic threat of AI-generated fake news for misinformation detection systems, though it is incremental as it builds on existing benchmarks.
The authors tackled the problem of detecting fake news generated by strategic human-AI collaboration, where falsehoods are embedded in credible narratives, by introducing the MANYFAKE benchmark with 6,798 articles. They found that state-of-the-art detectors perform well on fully fabricated stories but struggle with subtle, optimized falsehoods.
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.