PRECISE extends PPI to ranking evaluation metrics with a computational reduction for hierarchical metrics, showing standard error reduction on ESCI and correct identification of best system variant in production.
Proceedings of the AAAI Conference on Artificial Intelligence , author=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference
PRECISE extends PPI to ranking evaluation metrics with a computational reduction for hierarchical metrics, showing standard error reduction on ESCI and correct identification of best system variant in production.