Submodular maximization under a Gaussian model selects small benchmark subsets that outperform random selection for imputing leaderboard scores, with mutual information better than entropy at small sizes.
MassiveIntentClassification is the most stable top pick (10/10, mean rank 2.9), followed by STS15 and STS17
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Submodular Benchmark Selection
Submodular maximization under a Gaussian model selects small benchmark subsets that outperform random selection for imputing leaderboard scores, with mutual information better than entropy at small sizes.