← all papers · overview

Don't Always Pick The Highest-performing Model: An Information Theoretic View Of LLM Ensemble Selection

Abstract

Large language models (LLMs) are often ensembled together to improve overall reliability and robustness, but in practice models are strongly correlated. This raises a fundamental question: which models should be selected when forming an LLM ensemble? We formulate budgeted ensemble selection as maximizing the mutual information between the true label and predictions of the selected models. Furtherm

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).