BBC/EBU study says AI news summaries fail ~half the time

Tombstone icon
Oct 2025

A BBC audit of 2,700 news questions asked in 14 languages found that Gemini, Copilot, ChatGPT, and Perplexity mangled 45% of the answers, usually by hallucinating facts or stripping out attribution. The consortium logged serious sourcing lapses in a third of responses, including 72% of Gemini replies, plus outdated or fabricated claims about public-policy news, reinforcing fears that AI assistants are siphoning audiences while distorting the journalism they quote.

Incident Details

Perpetrator:AI Product
Severity:Facepalm
Blast Radius:Public-service broadcasters warn that unreliable AI summaries erode trust in news and drive audiences away from verified outlets.

Tech Stack

Google GeminiMicrosoft CopilotOpenAI ChatGPTPerplexity AI assistantBBC/EBU benchmarking toolkit

References