Beyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM Arenas
Vector-Borda Empirical-Gap Elimination (VB-EGE) is presented, a fixed-confidence adaptive sampling algorithm for efficiently identifying models on the Pareto frontier in arena-style evaluation and established a worst-case lower bound showing that VB-EGE is minimax-optimal up to logarithmic factors.