arXiv Computation and Language October 15, 2026 By Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu, Wenhui Tan, Jipei He, Ruihua Song, Rita Cucchiara

Frustratingly Easy Majority Voting Using Length Conditioning

Read the original on arXiv Computation and Language →

The paper introduces Length‑Conditioned Majority Voting (LCMV), a test‑time training method that enhances the standard Majority Voting (MV) technique for Large Language Models (LLMs). LCMV incorporates an empirical bias that longer Chain‑of‑Thoughts (CoTs) are less likely to be correct by modeling a length‑conditioned prior with a logistic function. This prior is adapted on unlabeled test data without fine‑tuning the LLM, and the resulting weighted votes consistently outperform standard MV and other length‑ or confidence‑based aggregation strategies across multiple reasoning benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Oct 14

Frustratingly Easy Majority Voting Using Length Conditioning

Majority Voting (MV) is a simple and widely used strategy which improves the reasoning accuracy of Large Language Models (LLMs) by allocating additional inference-time computation. Specifically, in MV...

llms fine-tuning benchmarks safety

arXiv AI

Aug 18

Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning

arXiv:2608. 15065v1 Announce Type: new Abstract: Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deployment.

By Chanhee Park, Sungbin Han, Jeongho Yoon, Seongtae Hong, Heuiseok Lim

efficiency

arXiv AI

Jun 3

Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge

arXiv:2512. 03019v2 Announce Type: replace-cross Abstract: Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation rules (majority vote, soft self-consistency, or instruction-based self-aggregation) are inconsistent when ties are allowed.

By Hamid Dadkhahi, Firas Trabelsi, Parker Riley, Juraj Juraska, Mehdi Mirzazadeh

llms benchmarks

arXiv AI

Jul 1

Optimal Self-Consistency for Efficient Reasoning with Large Language Models

arXiv:2511. 12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning.

By Austin Feng, Marius Alonso, Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko

llms benchmarks

arXiv AI

Sep 24

Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement

arXiv:2609.27165v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix backgr...

By Yuhe Wu, Rui Qian, Guangyu Wang, Yuran Chen, Yuanchao Zhu, Junjie Yang, Zhengheng Li, Jiulin Cai, Tianyi Zhang, Zihan Dong, Jiaxin Liu, Yujie Chen, Guang Zhang

llms benchmarks

arXiv Computation and Language

Sep 1

Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs

arXiv:2608.29257v1 Announce Type: new Abstract: Multiple-choice questions (MCQs) are a standard format for evaluating large language models (LLMs), yet the popularity of answer options can confound e...

By Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani, Mahmoud Abdalla, Adam Jatowt

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Frustratingly Easy Majority Voting Using Length Conditioning

Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning

Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge

Optimal Self-Consistency for Efficient Reasoning with Large Language Models

Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement

Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs