Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A structural dichotomy classifies full conjunctive queries without self-joins as polynomial-time solvable or NP-hard for minimizing input deletions to eliminate k output tuples, with exact and approximation algorithms.
citing papers explorer
-
Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
-
Generalized Deletion Propagation on Counting Conjunctive Query Answers
A structural dichotomy classifies full conjunctive queries without self-joins as polynomial-time solvable or NP-hard for minimizing input deletions to eliminate k output tuples, with exact and approximation algorithms.