When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

Title:When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

Abstract:Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. We show that piping the signals every sample carries into a delegation-based aggregator (Propagational Proxy Voting, PPV) yields an unsupervised consensus rule that beats majority on MMLU-Pro by +1.5 pp overall and +2.24 pp on the non-trivial subset (paired McNemar p ~ 1.0e-14, n = 8,099). Majority discards two free signals every sample carries: within-group letter entropy and between-group reasoning geometry. PPV exposes two per-voter levers that consume exactly these signals: WHEN (how much weight a voter keeps on its own pick) and WHOM (how it splits the remainder across peers). We drive WHEN with letter entropy and WHOM with per-question-centered embedding cosine. The method needs no gold labels and no auxiliary training: per question, we partition 128 sampled generations into 16 groups, compute each group's letter-level semantic entropy and reasoning embedding centroid, and feed both into a stochastic delegation matrix whose stationary distribution selects the consensus answer. We walk through an example in which PPV overturns a clear 10-6 majority for the wrong letter: the 10-voter majority cluster is geometrically incoherent (mean within-cluster cosine -0.02) while the 6-voter minority is tight (+0.26), so propagated delegation mass concentrates on the minority's answer even though entropy alone would keep the majority ahead. We further report delegation strategies with negative results that constrain the design space for unsupervised LLM aggregation: no within-question ensemble of confidence modes closes the oracle gap.

Preprint. 16 pages, 5 figures, 4 tables

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2606.08098 [cs.AI]

(or arXiv:2606.08098v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.08098 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.