Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval

TL;DR

This paper introduces a multi-agent automated fact-checking system that improves accuracy, efficiency, and transparency in verifying claims by decomposing complex statements, retrieving credible evidence, and providing human-interpretable explanations.

Contribution

It presents a novel multi-agent framework that enhances automated fact-checking by integrating specialized agents for claim decomposition, targeted querying, evidence sourcing, and transparent verdict generation.

Findings

Achieves 12.3% higher Macro F1-score on benchmark datasets.

Effectively decomposes complex claims for better verification.

Provides transparent explanations for fact-checking decisions.

Abstract

The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with the volume and velocity of online content, prompting the integration of automated systems powered by Large Language Models (LLMs). However, existing automated approaches often face limitations, such as handling complex claims, ensuring source credibility, and maintaining transparency. This paper proposes a novel multi-agent system for automated fact-checking that enhances accuracy, efficiency, and explainability. The system comprises four specialized agents: an Input Ingestion Agent for claim decomposition, a Query Generation Agent for formulating targeted subqueries, an Evidence Retrieval Agent for sourcing credible evidence, and a Verdict Prediction Agent for synthesizing veracity judgments with human-interpretable explanations. Evaluated on benchmark datasets (FEVEROUS, HOVER, SciFact), the proposed system achieves a 12.3% improvement in Macro F1-score over baseline methods. The system effectively decomposes complex claims, retrieves reliable evidence from trusted sources, and generates transparent explanations for verification decisions. Our approach contributes to the growing field of automated fact-checking by providing a more accurate, efficient, and transparent verification methodology that aligns with human fact-checking practices while maintaining scalability for real-world applications. Our source code is available at https://github.com/HySonLab/FactAgent