The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News
Yuhan Liu, Yuxuan Liu, Xiaoqing Zhang, Xiuying Chen, Rui Yan
TL;DR
Fake news detection often sacrifices interpretability or fails to fully leverage LLMs' reasoning. The authors propose TruEDebate (TED), a multi-agent framework that embeds a formal Lincoln–Douglas style debate (DebateFlow) within a two-agent flow, complemented by InsightFlow for interpretability (Synthesis and Analysis). TED uses a role-aware encoder and a debate graph to integrate discourse with news content via interactive attention, enabling transparent justifications and accurate judgments. Across ARG-EN and ARG-CN, TED outperforms LLM-only, SLM-only, and hybrid baselines and shows robust performance across both open-source and closed-source backbones, with ablations validating the necessity of each component. This work advances interpretable, debate-driven fake-news detection and offers a versatile approach adaptable to various LLM backbones and settings.
Abstract
In today's digital environment, the rapid propagation of fake news via social networks poses significant social challenges. Most existing detection methods either employ traditional classification models, which suffer from low interpretability and limited generalization capabilities, or craft specific prompts for large language models (LLMs) to produce explanations and results directly, failing to leverage LLMs' reasoning abilities fully. Inspired by the saying that "truth becomes clearer through debate," our study introduces a novel multi-agent system with LLMs named TruEDebate (TED) to enhance the interpretability and effectiveness of fake news detection. TED employs a rigorous debate process inspired by formal debate settings. Central to our approach are two innovative components: the DebateFlow Agents and the InsightFlow Agents. The DebateFlow Agents organize agents into two teams, where one supports and the other challenges the truth of the news. These agents engage in opening statements, cross-examination, rebuttal, and closing statements, simulating a rigorous debate process akin to human discourse analysis, allowing for a thorough evaluation of news content. Concurrently, the InsightFlow Agents consist of two specialized sub-agents: the Synthesis Agent and the Analysis Agent. The Synthesis Agent summarizes the debates and provides an overarching viewpoint, ensuring a coherent and comprehensive evaluation. The Analysis Agent, which includes a role-aware encoder and a debate graph, integrates role embeddings and models the interactions between debate roles and arguments using an attention mechanism, providing the final judgment.