Rank-weighted adaptive sampling of which model to score next recovers top-model rankings from WMT human evaluation data with less budget than uniform evaluation.
Journal of Machine Learning Research 7(39):1079–1105
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamically Allocating Evaluation Effort for Model Ranking
Rank-weighted adaptive sampling of which model to score next recovers top-model rankings from WMT human evaluation data with less budget than uniform evaluation.