为什么大语言模型能够生成正确的思维链？
Why Can Large Language Models Generate Correct Chain-of-Thoughts?
AI总结：
本文通过双层层次图模型和几何收敛速率，从理论上解释了大语言模型在思维链提示下能够生成正确思维序列并提升推理任务性能的原因。
摘要：
本文深入探讨大语言模型（LLMs）的能力，特别聚焦于推进对思维链提示（chain-of-thought prompting）的理论理解。我们研究如何有效引导LLMs生成连贯的思维链。为实现这一目标，我们引入了一个专为自然语言生成设计的双层层次图模型。在该框架内，我们建立了一个具有说服力的几何收敛速率，用于衡量LLM生成的思维链与源自真实语言的思维链相比的可能性。我们的发现为LLMs能够产生正确思维序列的能力提供了理论依据，（潜在地）解释了在需要推理技能的任务中性能提升的原因。
英文摘要：
This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a coherent chain of thoughts. To achieve this, we introduce a two-level hierarchical graphical model tailored for natural language generation. Within this framework, we establish a compelling geometrical convergence rate that gauges the likelihood of an LLM-generated chain of thoughts compared to those originating from the true language. Our findings provide a theoretical justification for the ability of LLMs to produce the correct sequence of thoughts (potentially) explaining performance gains in tasks demanding reasoning skills.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
