A weighted swap law, combining accuracy gap and accuracy-adjusted error correlation, predicts LLM ensemble lift, though transfer to one benchmark is rank-level only.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift
A weighted swap law, combining accuracy gap and accuracy-adjusted error correlation, predicts LLM ensemble lift, though transfer to one benchmark is rank-level only.