Large Language Models (LLMs) are versatile, yet they often falter in tasks requiring deep and reliable reasoning due to issues like hallucinations, limiting their applicability in critical scenarios. This paper introduces a rigorously designed framework for creating LLMs that effectively anchor knowledge and employ a closed-loop reasoning process, enhancing their capability for in-depth analysis. We dissect the framework to illustrate the contribution of each component to the LLMs' performance, offering a theoretical assurance of improved reasoning under well-defined assumptions.

翻译：大型语言模型（LLMs）虽功能多样，但在需要深度可靠推理的任务中常因幻觉等问题表现欠佳，限制了其在关键场景中的应用。本文提出一个严谨设计的框架，用于构建能有效锚定知识并采用闭环推理过程的大语言模型，从而增强其深度分析能力。我们剖析该框架以阐释各组件对LLMs性能的贡献，并在明确假设下为改进推理能力提供理论保证。