Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
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}
引用
@article{arxiv.2407.21358,
title = {Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs},
author = {Elan Markowitz and Anil Ramakrishna and Jwala Dhamala and Ninareh Mehrabi and Charith Peris and Rahul Gupta and Kai-Wei Chang and Aram Galstyan},
journal= {arXiv preprint arXiv:2407.21358},
year = {2024}
}
备注
Accepted for publication at the ACL 2024 Conference