English(EN) Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs

新理论解释了大型语言模型中的思维链泛化能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 12:38

一篇新论文探讨了大型语言模型（LLMs）中思维链（CoT）推理的理论基础，重点关注其分布外（OOD）泛化能力。该研究提出，CoT通过重复应用共享的单步预测器来组合可重用的转换，从而实现OOD泛化。理论分析表明，OOD任务风险受限于分布内子任务风险之和，该风险由每步输出令牌数相关的因子以及依赖于推理步骤和训练样本数量的估计项进行缩放。在Atom-Task和GSM8K数据集上进行的实验似乎支持这些理论发现，并强调了显式状态跟踪对于有效CoT泛化的重要性。 AI

影响为理解和潜在地改进大型语言模型的推理和泛化能力提供了理论框架。

排序理由学术论文，详细介绍了大型语言模型推理机制的理论分析和实验验证。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了大型语言模型推理机制的理论分析和实验验证。[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: 6 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-11-04 12:38

理解大型语言模型中思维链推理的分布外泛化能力

Chain-of-Thought (CoT) reasoning substantially improves Large Language Models (LLMs), yet its out-of-distribution (OOD) generalization mechanism remains theoretically underexplored. We study CoT as compositional OOD generalization: the target task lacks complete reasoning traject…

本文如何被排名

报道来源 [1]

理解大型语言模型中思维链推理的分布外泛化能力

相关实体

相关话题