LONDON: A major international study by 22 leading public service media organizations has revealed that popular AI assistants fail to deliver accurate news nearly 45% of the time, regardless of language or region.
The research assessed platforms including ChatGPT, Microsoft Copilot, Google Gemini, and Perplexity AI, examining their performance across key journalism standards such as accuracy, sourcing, context, and editorial judgment.
According to the findings, 53% of AI-generated answers had significant issues, 31% contained sourcing errors, and 20% included factual inaccuracies, as reported by Deutsche Welle (DW).
The study, coordinated by the European Broadcasting Union (EBU), reviewed over 3,000 AI responses from 18 countries, using multiple languages. Journalists compared answers on common questions—such as “What is the Ukraine minerals deal?” and “Can Trump run for a third term?”—against verified editorial sources.
“These failings are not isolated incidents,” said Jean Philip De Tender, Deputy Director General of the EBU. “They are systemic, cross-border, and multilingual—and they endanger public trust.”
Read More: AI Assistants Distort News in Nearly Half Their Responses
The EBU warned that widespread misinformation from AI assistants risks undermining democracy by eroding people’s confidence in reliable news sources.
This research builds on a BBC investigation in February 2025, which found that over half of all AI-generated answers had notable problems. The latest study noted minor improvements, but persistent accuracy issues across all platforms.
Among the tested chatbots, Google’s Gemini performed the worst, with 72% of its responses showing sourcing flaws, while Microsoft’s Copilot also ranked poorly.
AI-powered assistants are becoming a mainstream source of news. The Reuters Institute’s Digital News Report 2025 found that 7% of online users rely on AI chatbots for news — rising to 15% among people under 25.
Read More: AI and the Fight for Trustworthy News
To address these concerns, the EBU and partner broadcasters have launched a campaign titled “Facts In: Facts Out”, urging AI companies to uphold journalistic integrity. The initiative calls on regulators to enforce digital information laws and ensure independent monitoring of AI systems.
The campaign’s message is clear: “If facts go in, facts must come out. AI tools must not compromise the integrity of the news they use.”