When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation
Not on the map. Why?
Abstract (arXiv)
Increasing a voting budget can improve or reduce population accuracy, and an initial gain or loss need not persist. We give a complete structural classification of these curves for binary unweighted majority under infinitely exchangeable correctness indicators, with an arbitrary latent success-probability law Pi. The classification is encoded by the signed voting signature ω_Pi(B)=int 1q(1-q)∈ B(2q-1),Pi(,d q). The complete odd-budget curve and this signature determine each other: the initial accuracy gives its total signed mass, and successive budget increments give its higher moments. Reflection-symmetric differences between latent laws are exactly the changes invisible to voting. A weighted total-variation constraint characterizes every attainable signature, and a minimum-mass allocation to the two reflected branches, completed by symmetric probability mass, gives every population producing its curve. Consequently, the full curve identifies the latent population precisely when no symmetric mass remains to redistribute.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 7 May 2026.
Builds on
21 of 30 references.
References · 21
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2023Let's Verify Step by Stepcited by 3,598
- 2025s1: Simple test-time scalingcited by 1,311
- 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
- 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
- 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
- 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
- 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
- 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 156
- 2020Uncertainty Quantification and Deep Ensemblescited by 138
9 more
- 2025Confidence Improves Self-Consistency in LLMscited by 111
- 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
- 2021Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learningcited by 81
- 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 62
- 2020Self-regularizing Property of Nonparametric Maximum Likelihood Estimator in Mixture Modelscited by 16
- 2019Maximum Likelihood Estimation for Learning Populations of Parameterscited by 11
- 2025The Consistency Hypothesis in Uncertainty Quantification for Large Language Modelscited by 6
- 2022On Efficient and Scalable Computation of the Nonparametric Maximum Likelihood Estimator in Mixture Modelscited by 5
- 2026Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inferencecited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.