Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score

• URL: http://arxiv.org/abs/2604.12196v1
• Date: Tue, 14 Apr 2026 02:02:20 GMT
• Title: Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score
• Abstract summary: Radial Consensus Score (RCS) is a simple, efficient, and training-free method for best-of-N selection.<n>RCS models semantic consensus by computing a weighted Fréchet mean (semantic center) of answer embeddings and ranking candidates by their radial distance to this center.
• Score: 13.41454380481593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) frequently generate multiple candidate responses for a given prompt, yet selecting the most reliable one remains challenging, especially when correctness diverges from surface-level majority agreement. Existing approaches, such as self-consistency, rely on discrete voting, while probability-based methods often fail to capture relationships among candidate answers or tend to underweight high-quality but less frequent responses, and do not fully leverage the geometric structure of answer representations. To address these limitations, we introduce Radial Consensus Score (RCS), a simple, efficient, and training-free method for best-of-N selection. RCS models semantic consensus by computing a weighted Fréchet mean (semantic center) of answer embeddings and ranking candidates by their radial distance to this center. Importantly, RCS provides a general framework that supports multiple weighting schemes, including uniform, frequency-based, and probability-based variants, enabling flexible integration of agreement signals and model confidence while remaining fully applicable in black-box settings. Extensive experiments across seven benchmarks covering short-form QA and long-form reasoning tasks, and five open-weight models, demonstrate that RCS variants consistently outperform strong baselines, with gains becoming more pronounced as the sampling budget increases. RCS also serves as an effective drop-in replacement for majority voting in multi-agent debate and exhibits strong robustness in black-box scenarios. Overall, these results highlight geometric consensus as a scalable and broadly applicable principle for reliable answer selection, extending beyond majority voting to more expressive and robust aggregation in LLM inference.

Related papers

• Robust Conformalized Selection with Noisy Responses [23.306273801765297]
  Conformalized selection has been widely applied to select high-quality candidates from large datasets.<n>We formulate the above tasks as selecting candidates with true predicted labels or with responses exceeding certain values.<n>We propose Robust Conformalized Selection (RCS), a unified framework for selective classification with valid FDR control under general label contamination.
  arXiv  Detail & Related papers  (2026-07-25T01:51:46Z)
• CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency [9.50454647525075]
  We introduce CQC-RAG, a framework that co-designs query-level diversity injection with cross-Query Consistency evaluation.<n>CQC-RAG rewrites the original question into diverse but meaning-preserving queries.<n>It applies an evidence-grounded protocol to extract answer-evidence pairs and selects answers according to confidence stability.
  arXiv  Detail & Related papers  (2026-06-11T15:01:49Z)
• Boosting Self-Consistency with Ranking [56.38798757709555]
  Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer.<n>We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem.
  arXiv  Detail & Related papers  (2026-06-03T16:12:30Z)
• Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning [12.354777054071379]
  Test-time reinforcement learning mitigates reliance on annotated data by using majority voting results as pseudo-labels.<n>This voting strategy often induces confirmation bias and suffers from sparse rewards, limiting the overall performance.<n>We propose subgroup-specific step-wise confidence-weighted pseudo-label estimation (SCOPE) to address these issues.
  arXiv  Detail & Related papers  (2025-12-17T07:21:54Z)
• Robust Preference Alignment via Directional Neighborhood Consensus [13.313830197011983]
  We introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus.<n>RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool.<n>Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.
  arXiv  Detail & Related papers  (2025-10-23T12:39:20Z)
• The Majority is not always right: RL training for solution aggregation [53.1050856072799]
  We train an aggregator model to review, reconcile, and synthesize a final, correct answer.<n>A key ingredient is careful balancing of easy and hard training examples.<n>We find our method, AggLM, outperforms both strong rule-based and reward-model baselines.
  arXiv  Detail & Related papers  (2025-09-08T16:39:38Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Multivariate Conformal Selection [9.431551477608528]
  We propose a generalization of Conformal Selection (CS) to provide rigorous uncertainty quantification.<n>We present two variants: mCS-dist, using distance-based scores, and mCS-learn, which learns optimal scores via differentiable optimization.<n>Experiments on simulated and real-world datasets demonstrate that mCS significantly improves selection power while maintaining False Discovery Rate (FDR) control.
  arXiv  Detail & Related papers  (2025-05-01T23:33:57Z)
• More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment [80.04449725137177]
  Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback.<n>Our study reveals a striking, safety-specific phenomenon associated with DPO alignment.<n>Using solely self-generated responses for both chosen and rejected pairs significantly outperforms configurations that incorporate responses from stronger models.
  arXiv  Detail & Related papers  (2025-04-03T00:36:40Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [75.1351701045874]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs)<n>We propose self-certainty, a novel and efficient metric that leverages the inherent probability distribution of LLM outputs to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.