Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs

TL;DR

Tree-of-Traversals is a zero-shot reasoning algorithm that enhances black-box language models with knowledge graphs by enabling tree search over reasoning paths, significantly improving question answering performance.

Contribution

It introduces a novel zero-shot reasoning method that integrates knowledge graphs with black-box LLMs through tree search, without additional training.

Findings

Significant performance improvements on question answering tasks.

Effective augmentation of LLMs with external knowledge graphs.

Applicable to multiple benchmark datasets.

Abstract

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}