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

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference arXiv:2606.08098v1 Announce Type: new 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 su