MADRAG combines multi-agent debate with retrieval-augmented generation to produce training-free analytic essay scores that outperform prompt baselines and approach supervised systems.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
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.