Veracity: An Open-Source AI Fact-Checking System
Veracity: An Open-Source AI Fact-Checking System
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.
Taylor Lynn Curtis、Maximilian Puelma Touzel、William Garneau、Manon Gruaz、Mike Pinder、Li Wei Wang、Sukanya Krishna、Luda Cohen、Jean-Fran?§ois Godbout、Reihaneh Rabbany、Kellin Pelrine
计算技术、计算机技术
Taylor Lynn Curtis,Maximilian Puelma Touzel,William Garneau,Manon Gruaz,Mike Pinder,Li Wei Wang,Sukanya Krishna,Luda Cohen,Jean-Fran?§ois Godbout,Reihaneh Rabbany,Kellin Pelrine.Veracity: An Open-Source AI Fact-Checking System[EB/OL].(2025-06-18)[2025-07-17].https://arxiv.org/abs/2506.15794.点此复制
评论