LLMs Can Assist with Proposal Selection at Large User Facilities

This paper explores how large language models (LLMs) can enhance the proposal selection process at large user facilities. It offers a scalable, consistent, and cost-effective alternative to traditional human review, which often suffers from weak inter-proposal correlations, reviewer bias, and inconsistency. LLMs can provide a more rigorous basis for ranking and perform advanced analyses such as quantitative assessment of proposal similarity.