
Xuemei Gu, Mario Krenn · Proceedings of the National Academy of Sciences 2026 · 2026
DOI: 10.1073/pnas.2611349123
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
The rapid growth of scientific literature makes it increasingly challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern AI systems offer new opportunities for scientific ideation, but how compelling are AI-generated ideas, and how can their quality be improved? Here, we introduce SCIMUSE , which generates personalized research ideas using a knowledge graph of 58 million papers and a large language model (LLM). A central focus of this work is to understand how interesting these ideas are. Therefore, we conducted a large-scale evaluation in which more than 100 research group leaders—spanning the natural sciences to the humanities—rated over 4,400 personalized ideas according to their level of interest. Overall, expert ratings were modest (mean 2.40 on a 5-point scale, most common rating 1), while 24.9% of ideas were rated 4 or 5. We find that supplying concept pairs selected using the knowledge graph does not improve expert-rated interest over a titles-only GPT baseline. High-citation-predicted pairs even showed a weak tendency (1.94 σ ) toward lower interest than random pairs. Nevertheless, graph features can be used to control properties of ideas, and, using this unique evaluation dataset, we show that idea interest can be predicted with both a supervised neural network based on graph features and a zero-shot ranking approach based on an LLM. Our work provides an AI methodology for generating scientific ideas and a large-scale interdisciplinary expert evaluation, paving the way to study and improve difficult-to-measure metrics such as expert-perceived scientific interestingness.
Last synced
This work has 66 recorded citations, but citing papers have not been linked locally yet.
No comments yet — start the discussion below.