Temporal evolution of large language models (LLMs) in oncology.

J Transl Med · 2025 · PMC12584546 · PMID 41188901

Europe PMC DOI

hedged sentence

—

closest p

—

boldest claim

The sentences

did not reach statistical significanceno p-value reported

While the performance decline in ChatGPT-3.5 did not reach statistical significance, ChatGPT-4 exhibited a statistically significant reduction in accuracy.

also in 111,027 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.