AINeutralarXiv – CS AI · 18h ago6/10
🧠
When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference
Researchers introduce Propagational Proxy Voting (PPV), an unsupervised aggregation method for multi-sample LLM inference that outperforms standard majority voting on MMLU-Pro benchmarks by leveraging semantic entropy and reasoning geometry signals. The method achieves +1.5 percentage point overall improvement and +2.24 pp on difficult questions without requiring labeled data or auxiliary training.