Veracity: An Open-Source AI Fact-Checking System

TL;DR

Veracity is an open-source AI system that combines large language models and web retrieval to provide transparent, multilingual fact-checking with explanations, aiming to combat misinformation and promote media literacy.

Contribution

The paper introduces Veracity, a novel open-source fact-checking system that integrates LLMs and web retrieval for transparent, multilingual veracity assessments with user-friendly explanations.

Findings

Effective detection of misinformation across multiple languages.

Provides grounded explanations for veracity assessments.

Enhances media literacy through transparent reasoning.

Abstract

The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.