Integrating large language models into prostate cancer training: evidence from comparative benchmarking and a pilot randomized trial

Xuhao Liu, Minfeng Chen, Yi Cai · 2026

Read Integrating large language models into prostate cancer training: evidence from comparative benchmarking and a pilot randomized trial by Xuhao Liu, Minfeng Chen, Yi Cai (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13474703.txt.

Description

Xuhao Liu, Minfeng Chen, and Yi Cai test chatbots as teaching aids in 2026 for prostate cancer training of urology residents. Three leading models answered a forty-item question bank and were graded blind by experts. The top scorer then joined a small randomized teaching trial with thirty-four residents. Both trial groups got the same lectures, with one group allowed model help for study questions.

One model, DeepSeek R1, ranked first, with an edge on higher-order and creative questions. The aided group scored about ten points higher on a closed-book exam. Gains concentrated in choice questions and research items, not in team case review. Teachers and students both rated the aid well, which supports careful classroom use.

Catalog record

CREATORXuhao Liu, Minfeng Chen, Yi Cai
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE48837
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13474703

Browse the full library · About the Tower of Babel