Prominent chatbots routinely exaggerate science findings, study shows

When summarizing scientific studies, large language models (LLMs) like ChatGPT and DeepSeek produce inaccurate conclusions in up to 73% of cases, according to a study by Uwe Peters (Utrecht University) and Benjamin Chin-Yee (Western University, Canada/University of Cambridge, UK). The researchers tested the most prominent LLMs and analyzed thousands of chatbot-generated science summaries, revealing that most models consistently produced broader conclusions than those in the summarized texts.

This article is brought to you by Phys.Org.