Percentage of responses with specific or generic links to sources or both

Perplexity.ai linked only to specific sources in almost all responses, whereas ChatGPT-4o did so for 57% of its responses, with 13% of its responses containing at least one link to a generic source.

(Please use a modern browser to see the interactive version of this visualization)

Note: We prompted each chatbot with 100 election-related questions and fact-checks about the 2024 UK general election in the two weeks before the election on 4 July 2024. We coded if chatbots provided specific sources in their responses. We defined a specific source as a page on a clearly identifiable topic relating to a claim (e.g. www.website.com/politics/election_2024_polling in a question about polling results) in comparison with a generic source (e.g. www.website.com). Bing.com was not counted as a source for ChatGPT-4o.

Source: Data from the factsheet How Generative AI Chatbots Responded to Questions and Fact-Checks About the 2024 UK General Election, published in September 2024.