Researchers tested ChatGPT’s ability to identify sources for 200 citations from 20 publications. Of these, 40 were from publishers who blocked access to OpenAI tools. ChatGPT still provided strong but incorrect answers to most of these.
In total, the chatbot answered partially or completely incorrectly 153 times and acknowledged its uncertainty in only 7 cases. For example, he misquoted an excerpt from the Orlando Sentinel editor’s letter to Time magazine, citing the copied article rather than the original New York Times article.
OpenAI said the “test is not representative of typical usage” and promised to improve search accuracy.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
