The Future of Combating Rumors? Retrieval, Discrimination, and Generation

TL;DR

This paper proposes a comprehensive AI-based system for rumor detection and debunking that combines retrieval, discrimination, and generation to provide accurate, explainable, and cost-effective misinformation refutation.

Contribution

It introduces an integrated approach using an ECCW module, real-time knowledge retrieval, and prompt engineering with LLMs to enhance rumor debunking without fine-tuning.

Findings

High-precision credibility assessment achieved

Effective retrieval of relevant debunking knowledge

Satisfactory discrimination and explanation without fine-tuning

Abstract

Artificial Intelligence Generated Content (AIGC) technology development has facilitated the creation of rumors with misinformation, impacting societal, economic, and political ecosystems, challenging democracy. Current rumor detection efforts fall short by merely labeling potentially misinformation (classification task), inadequately addressing the issue, and it is unrealistic to have authoritative institutions debunk every piece of information on social media. Our proposed comprehensive debunking process not only detects rumors but also provides explanatory generated content to refute the authenticity of the information. The Expert-Citizen Collective Wisdom (ECCW) module we designed aensures high-precision assessment of the credibility of information and the retrieval module is responsible for retrieving relevant knowledge from a Real-time updated debunking database based on information keywords. By using prompt engineering techniques, we feed results and knowledge into a LLM (Large Language Model), achieving satisfactory discrimination and explanatory effects while eliminating the need for fine-tuning, saving computational costs, and contributing to debunking efforts.