Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
This addresses the challenge of augmenting LLMs with reliable, structured knowledge for improved reasoning in AI applications, representing a novel integration approach rather than an incremental improvement.
The paper tackles the problem of integrating knowledge graphs (KGs) with black-box large language models (LLMs) to enhance reasoning, introducing Tree-of-Traversals, a zero-shot algorithm that enables LLMs to perform tree search over KGs, resulting in significant performance improvements on question answering and KG question answering tasks.
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}