arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.11135cs.CLcs.AI

知识增强大型语言模型的原则性框架

A Principled Framework for Knowledge-enhanced Large Language Model

Northwestern University(西北大学);IDEA Research, International Digital Economy Academy(国际数字经济学院IDEA研究院);The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

Saizhuo Wang, Zhihan Liu, Zhaoran Wang, Jian Guo

AI总结:

本文提出一个严格设计的框架,通过锚定知识和闭环推理过程创建大型语言模型,增强其深度分析能力,并在明确假设下提供改进推理的理论保证。

摘要:

大型语言模型(LLMs)具有多功能性,但由于幻觉等问题,在需要深度且可靠推理的任务中常表现不足,限制了其在关键场景中的适用性。本文提出了一个严格设计的框架,用于创建能有效锚定知识并采用闭环推理过程的LLMs,增强其深度分析能力。我们剖析了该框架,展示了各组件对LLMs性能的贡献,并在明确定义的假设下提供了改进推理的理论保证。

英文摘要:

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.

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。

↑