Best-of-$\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling

Junpei Komiyama, Daisuke Oba, Masafumi Oyamada

We study best-of-$N$ for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit $N\to \infty$, which we denote as \boinf…