English(EN) Frustratingly Easy Majority Voting Using Length Conditioning

新方法通过链长条件投票来改进LLM推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员引入了长度条件多数投票（LCMV），这是一种提高大型语言模型（LLM）推理准确性的新方法。LCMV利用了较长的思维链（CoTs）通常准确性较低的观察结果。该方法将其建模为长度条件先验概率，在测试时使用无标签数据进行调整，而无需对LLM进行微调。然后，这种调整后的先验会加权采样答案的投票，在各种LLM和推理基准测试中始终优于标准的多数投票和其他聚合策略。 AI

影响通过根据链长优化投票聚合来增强LLM的推理能力，有可能提高复杂任务的性能。

排序理由该集群包含一篇详细介绍改进LLM推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍改进LLM推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu, Wenhui Tan, Jipei He, Ruihua Song, Rita Cucchiara · 2026-10-15 04:00

利用长度条件实现令人沮丧的简单多数投票

arXiv:2610.19890v1 Announce Type: new Abstract: 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 multiple Chain-of-Thoughts (CoT…

本文如何被排名

报道来源 [1]

利用长度条件实现令人沮丧的简单多数投票

相关实体

相关话题