Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift

Excerpt

arXiv:2607.17384v3 Announce Type: replace-cross Abstract: This paper provides an experimentally verified formal law for calculating the uplift that diversity of thought provides in Large Language Model (LLM) ensembles. From first principles, we derive an exact decomposition of LLM ensemble lift into rescue and damage masses, which yields a compact heuristic for calculating uplift. From this we extract the metrics which predict ensemble performance: an accuracy-adjusted correctness correlation, $