ChatGPT4o, Deepseek, and Grok 3 distort scientific references differently when wrestling with retracted articles on stem cells - a real challenge to applications of AI in the medical field (Preprint)

Abstract

<sec> <title>UNSTRUCTURED</title> DeepSeek and Grok 3 appear as strong competitors to AI models, particularly the widely accepted model, ChatGPT. The accuracy of the utilization of data in retracted scientific articles has proven to be a significant challenge for AI as an assistant in scientific research. It is critical to understand whether and how three AI models handle information from retracted articles when they answer scientific questions. Here we show that these three models utilized 84 out of 93 retracted articles in their answers about stem cells. ChatGPT4o retrieved 74 out of 93 (80%) articles and recognized the retract status for 46 (62%) of them. DeepSeek only found one retracted article and did not realize its retraction status. Grok 4 retrieved 69 (74%) articles and recognized the retraction status of 46 (67%) of them. In case when the correct retracted articles were not identified, ChatGPT fabricated articles 5 times out of 19 (26%) for its answers. Grok 3 fabricated 15 articles out of 24 (63%) for its answers. In 82 times of 93 (88%) answers, DeepSeek fabricated the articles in various forms. The answering styles from ChatGPT, DeepSeek, and Grok 3 are characterized by accurate and straightforward, a tangential structure and guesswork, and complete and thorough answers, respectively. Analysis with non-retracted articles revealed the similar patterns of these models. This data suggests that, while no model is perfect, DeepSeek performed worst when facing in-depth scientific real-world challenges. Much improvement has to be made before any of these AI models can become problem-free, valuable assistance for scientists. </sec>

Ähnliche Arbeiten