AI chatbots inaccurately "summarize"
2025-02-12 17:25:53.864505+01 by Dan Lyke 0 comments
Not news to anyone who's been using LLMs to create summaries, but AI chatbots unable to accurately summarise news, BBC finds.
In the study, the BBC asked ChatGPT, Copilot, Gemini and Perplexity to summarise 100 news stories and rated each answer.
It got journalists who were relevant experts in the subject of the article to rate the quality of answers from the AI assistants.
Deborah Turness - AI Distortion is new threat to trusted information