LLM-GAN: Construct Generative Adversarial Network Through Large Language Models For Explainable Fake News Detection
This addresses the problem of detecting fake news with explanations for users and platforms, but it is incremental as it adapts existing LLM and GAN concepts to a specific domain.
The paper tackles explainable fake news detection by proposing LLM-GAN, a framework that uses prompting to turn a large language model into a generator and detector for fake news, achieving improved prediction performance and explanation quality.
Explainable fake news detection predicts the authenticity of news items with annotated explanations. Today, Large Language Models (LLMs) are known for their powerful natural language understanding and explanation generation abilities. However, presenting LLMs for explainable fake news detection remains two main challenges. Firstly, fake news appears reasonable and could easily mislead LLMs, leaving them unable to understand the complex news-faking process. Secondly, utilizing LLMs for this task would generate both correct and incorrect explanations, which necessitates abundant labor in the loop. In this paper, we propose LLM-GAN, a novel framework that utilizes prompting mechanisms to enable an LLM to become Generator and Detector and for realistic fake news generation and detection. Our results demonstrate LLM-GAN's effectiveness in both prediction performance and explanation quality. We further showcase the integration of LLM-GAN to a cloud-native AI platform to provide better fake news detection service in the cloud.