
AI assistants ‘misrepresent’ news content 45 percent of the time, study finds.
Geneva, Oct 22 (EFE).
Artificial intelligence (AI) assistants misrepresented news stories nearly half the time, regardless of language, country, or platform, according to a study coordinated by the European Broadcasting Union (EBU).
The “intensive international study,” launched Wednesday at the EBU News Assembly in Naples, involved 22 public service media (PSM) organizations from 18 countries, including Spain’s RTVE.

Researchers found that 45 percent of AI-generated answers to news-related questions contained misinterpretations, while 20 percent had “major accuracy issues,” such as “hallucinated” details or outdated information.
AI assistants also struggled to correctly attribute information sources. About 31 percent of their answers either failed to mention the origin of the information or cited misleading or incorrect references.

“This research conclusively shows that these failings are not isolated incidents,” said EBU Media Director Jean Philip De Tender. “They are systemic, cross-border, and multilingual, and we believe this endangers public trust.”
The study, led by Britain’s BBC, analyzed more than 3,000 responses in 14 languages from four major AI tools, including ChatGPT, Copilot, Gemini and Perplexity. Researchers evaluated the answers for “accuracy, sourcing, distinguishing opinion from fact, and providing context.”

Gemini “performed worst,” with 76 percent of its responses showing significant issues, more than double the error rate of other assistants, largely due to its “poor sourcing performance.”
AI tools struggled most with fast-developing stories, complex timelines, detailed reporting, and topics requiring a clear separation between fact and opinion.

Nearly half of the AI explanations about US President Donald Trump’s tariffs contained major errors, as did responses regarding the death toll from this year’s earthquake in Myanmar and the US bombing of Yemen.
The EBU called for ongoing monitoring of AI assistants as they evolve and urged the European Union and its member states to strengthen protections for information integrity, digital services, and media pluralism. EFE
