大型語言模型尚無法自我修正推理。

摘要

大型語言模型（LLMs）以其在各種應用中無與倫比的文本生成能力而成為一項開創性技術。儘管如此，人們仍然關注其生成內容的準確性和適切性。一種當代方法論，即自我校正，已被提出作為解決這些問題的方法。本文基於這一前提，批判性地探討了自我校正在LLMs中的作用和效力，闡明了其真正潛力和局限性。我們研究的核心是內在自我校正的概念，即LLM試圖僅基於其固有能力來糾正其初始回應，而無需外部反饋的支持。在推理的背景下，我們的研究表明，LLMs在沒有外部反饋的情況下很難自我校正其回應，有時，甚至在自我校正後其性能可能會下降。基於這些見解，我們提出了未來研究和實際應用在這一領域的建議。

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.

大型語言模型尚無法自我修正推理。

Large Language Models Cannot Self-Correct Reasoning Yet

摘要

Support