Academic peer review is at the heart of scientific quality control, yet the process is slow and time-consuming. Technology that can predict peer review outcomes may help with this, for example by fast-tracking desk rejection decisions. While previous studies have demonstrated that Large Language Models (LLMs) can predict peer review outcomes to some extent, this paper introduces two new contexts and employs a more robust method—averaging multiple ChatGPT scores. Averaging 30 ChatGPT predictions, based on reviewer guidelines and using only the submitted titles and abstracts failed to predict peer review outcomes for F1000Research (Spearman’s rho=0.00). However, it produced mostly weak positive correlations with the quality dimensions of SciPost Physics (rho=0.25 for validity, rho=0.25 for originality, rho = 0.20 for significance, and rho = 0.08 for clarity) and a moderate positive correlation for papers from the International Conference on Learning Representations (ICLR) (rho=0.38). Including article full texts increased the correlation for ICLR (rho=0.46) and slightly improved it for F1000Research (rho=0.09), with variable effects on the four quality dimension correlations for SciPost LaTeX files. The use of simple chain-of-thought system prompts slightly increased the correlation for F1000Research (rho=0.10), marginally reduced it for ICLR (rho=0.37), and further decreased it for SciPost Physics (rho=0.16 for validity, rho=0.18 for originality, rho=0.18 for significance, and rho=0.05 for clarity). Overall, the results suggest that in some contexts, ChatGPT can produce weak pre-publication quality predictions. However, their effectiveness and the optimal strategies for employing them vary considerably across different platforms, journals, and conferences. Finally, the most suitable inputs for ChatGPT appear to differ depending on the platform.
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)