LLM-based tool scored 1,200 SoPs for an undergraduate research program using GPT models and a rubric, enabling coordinator shortlisting in 4 hours versus prior multi-week effort.
7 LLMs for High-V olume Application ReviewA PREPRINT Appendix A: Evaluation Rubric The following rubric was part of the evaluation prompt
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program
LLM-based tool scored 1,200 SoPs for an undergraduate research program using GPT models and a rubric, enabling coordinator shortlisting in 4 hours versus prior multi-week effort.