Veracity: An Open-Source AI Fact-Checking System

2025-06-18

AI Summary

Misinformation proliferation poses severe threats to public cognition and social stability, with generative AI exacerbating its dissemination risks. To address this, we propose an open-source, transparent, and interpretable AI-powered fact-checking system that integrates large language models (LLMs) with real-time web retrieval agents within a retrieval-augmented generation (RAG) framework, enabling end-to-end, multilingual veracity assessment of user-submitted claims. Our system introduces a novel, intuitive numerical credibility score, accompanied by provenance-based evidence and natural-language explanations. It features a chat-like, user-friendly interface designed to enhance verification efficiency and trust among non-expert users. Evaluated across multilingual scenarios, the system achieves high accuracy while ensuring interpretability and public comprehensibility. By prioritizing reproducibility, auditability, and transparency, it establishes a new paradigm for AI-driven fact-checking grounded in open science principles.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Combating misinformation using open-source AI fact-checking
• Analyzing claims with LLMs and web retrieval agents
• Providing transparent veracity assessments and explanations

Innovation

• Leverages LLMs and web retrieval agents
• Provides multilingual veracity assessments
• Features interactive messaging-like interface