大型语言模型尚不能自我纠正推理。

摘要

大型语言模型（LLMs）以其在各种应用中无与伦比的文本生成能力成为一项开创性技术。然而，人们仍然对其生成内容的准确性和适当性表示关注。一种当代方法论，即自我校正，被提出作为解决这些问题的方法。本文基于这一前提，对LLMs内部的自我校正在其中的作用和效力进行了批判性审视，阐明了其真正潜力和局限性。我们研究的核心是内在自我校正的概念，即LLMs尝试仅基于其固有能力校正其初始响应，而无需外部反馈的支持。在推理的背景下，我们的研究表明，LLMs在没有外部反馈的情况下很难自我校正其响应，有时甚至在自我校正后性能可能会下降。基于这些见解，我们为未来研究和实际应用在这一领域提出建议。

English

Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns persist regarding the accuracy and appropriateness of their generated content. A contemporary methodology, self-correction, has been proposed as a remedy to these issues. Building upon this premise, this paper critically examines the role and efficacy of self-correction within LLMs, shedding light on its true potential and limitations. Central to our investigation is the notion of intrinsic self-correction, whereby an LLM attempts to correct its initial responses based solely on its inherent capabilities, without the crutch of external feedback. In the context of reasoning, our research indicates that LLMs struggle to self-correct their responses without external feedback, and at times, their performance might even degrade post self-correction. Drawing from these insights, we offer suggestions for future research and practical applications in this field.

大型语言模型尚不能自我纠正推理。

Large Language Models Cannot Self-Correct Reasoning Yet

摘要

Support