AI chatbots fail at accurate news, major study reveals

Deutsche Welle (DW)CenterEN 4 min read 100% complete by Arthur SullivanOctober 25, 2025 at 04:26 PM

AI Summary

long article 4 min

A study conducted by 22 international public broadcasters, including DW and BBC, revealed that AI chatbots like ChatGPT, Microsoft's Copilot, Google's Gemini, and Perplexity AI misrepresent news content 45% of the time. The research evaluated criteria such as accuracy, sourcing, context provision, editorializing, and distinguishing fact from opinion. It found that nearly half of all responses had significant issues, with 31% having serious sourcing problems and 20% containing major factual errors. For instance, Olaf Scholz was incorrectly named German Chancellor after Friedrich Merz took the role, and Jens Stoltenberg was inaccurately listed as NATO secretary general when Mark Rutte held the position. The study highlights systemic issues across languages and territories, potentially endangering public trust in news accuracy.

Key Topics & Entities

Google 30% BBC 30% ChatGPT ×240% Microsoft ×240% DW ×350% Mark Rutte 50% Friedrich Merz 60% Jens Stoltenberg 70% Olaf Scholz 80%

Keywords

ai chatbots 100% news accuracy 90% factual errors 80% public broadcasters 70% study findings 60% information distortion 50% mediaglobal 40% dw (deutsche welle) 40%

Sentiment Analysis

Negative

Score: -0.40

Source Transparency

Source

Deutsche Welle (DW)

Political Lean

Center (-0.10)

Far LeftCenterFar Right

Classification Confidence

90%

This article was automatically classified using rule-based analysis. The political bias score ranges from -1 (far left) to +1 (far right).

Topic Connections

Explore how the topics in this article connect to other news stories

No topic relationship data available yet. This graph will appear once topic relationships have been computed.

ai chatbots news accuracy factual errors public broadcasters study findings information distortion mediaglobal dw (deutsche welle)

Explore Full Topic Graph