Can Large Language Models Provide Useful Feedback on Research Papers? A Large-Scale Empirical Analysis

Expert feedback lays the foundation of rigorous research. However, the rapid growth of scholarly production challenges the conventional scientific feedback mechanisms. High-quality peer reviews are increasingly difficult to obtain.

We created an automated pipeline using Generative Pretrained Transformer 4 (GPT-4) to provide comments on scientific papers. We evaluated the quality of GPT-4's feedback through two large-scale studies. We first quantitatively compared GPT-4's generated feedback with human peer reviewers' feedback in general scientific papers from 15 Nature family journals (3096 papers in total) and the International Conference on Learning Representations (ICLR) machine learning conference (1709 papers). To specifically assess GPT-4's performance on biomedical papers, we also analyzed a subset of 425 health sciences papers from the Nature portfolio and a random sample of 666 submissions to eLife. Additionally, we conducted a prospective user study with 308 researchers from 110 institutions in the fields of artificial intelligence and computational biology to understand how researchers perceive feedback generated by our system on their own papers.

The overlap in the points raised by GPT-4 and by human reviewers (average overlap of 30.85% for Nature journals and 39.23% for ICLR) is comparable with the overlap between two human reviewers (average overlap of 28.58% for Nature journals and 35.25% for ICLR). Results on eLife and a subset of health sciences papers as categorized by the Nature portfolio show similar patterns. In our prospective user study, more than half (57.4%) of the users found GPT-4-generated feedback helpful/very helpful, and 82.4% found it more beneficial than feedback from at least some human reviewers. We also identify several limitations of large language model (LLM)-generated feedback.

Through both retrospective and prospective evaluation, we find substantial overlap between LLM and human feedback as well as positive user perceptions regarding the usefulness of LLM feedback. Although human expert review should continue to be the foundation of the scientific process, LLM feedback could benefit researchers, especially when timely expert feedback is not available and in earlier stages of manuscript preparation. (Funded by the Chan-Zuckerberg Initiative and the Stanford Interdisciplinary Graduate Fellowship.).