遍历树:一种用于利用知识图谱增强黑盒语言模型的零样本推理算法
Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
AI总结:
本文提出零样本推理算法遍历树,通过树搜索结合知识图谱动作增强黑盒大语言模型,在问答和知识图谱问答任务上显著提升性能。
摘要:
知识图谱(KGs)通过提供可靠、结构化、领域特定且最新的外部知识来补充大语言模型(LLMs)。然而,知识图谱和大语言模型通常是分开开发的,必须在训练后进行集成。我们提出了遍历树(Tree-of-Traversals),这是一种新颖的零样本推理算法,能够利用一个或多个知识图谱增强黑盒大语言模型。该算法为大语言模型配备了与知识图谱交互的动作,并使其能够在可能的思维和动作上进行树搜索,以找到高置信度的推理路径。我们在两个流行的基准数据集上进行了评估。结果表明,遍历树在问答和知识图谱问答任务上显著提升了性能。代码可在 \url{https://github.com/amazon-science/tree-of-traversals} 获取。
英文摘要:
Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are often developed separately and must be integrated after training. We introduce Tree-of-Traversals, a novel zero-shot reasoning algorithm that enables augmentation of black-box LLMs with one or more KGs. The algorithm equips a LLM with actions for interfacing a KG and enables the LLM to perform tree search over possible thoughts and actions to find high confidence reasoning paths. We evaluate on two popular benchmark datasets. Our results show that Tree-of-Traversals significantly improves performance on question answering and KG question answering tasks. Code is available at \url{https://github.com/amazon-science/tree-of-traversals}
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。