AI-agent-based system for fact-checking support using large language models

Abstract

In today’s world, the problem of disinformation is becoming increasingly relevant due to the speed of information dissemination and the influence of social media. This article examines the impact of fake news on society and its political, economic and social consequences. Special attention is paid to the use of large language models (LLMs) to automate the fact-checking process. Describes the capabilities of LLMs in verifying information, including text analysis, comparison with reliable sources, and contextualization. At the same time, the risks of using LLMs to create fake news are highlighted. Proposes an architecture of an AI-based disinformation detection tool, which includes query processing modules, a database, work with web resources, and results analytics. This approach is aimed at improving the efficiency and accuracy of information verification.