Re:Most leading chatbots routinely exaggerate science findings
by kjfaejgoaeijhei on Monday May 26, 2025 @07:24PM
(#44102565)
The article doesn't, but you can go to the "more information" section and keep digging:
"To systematically assess differences between LLM-generated and human-written summaries, we also collected the corresponding expert-written summaries from NEJM Journal Watch (henceforth ‘NEJM JW’)"
"To systematically assess differences between LLM-generated and human-written summaries, we also collected the corresponding expert-written summaries from NEJM Journal Watch (henceforth ‘NEJM JW’)"