Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
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}
Code (1)
Tasks
Knowledge GraphsQuestion AnsweringSimilar Papers 제목 키워드 기반
Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs
Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper investigates whether structured, tree-ba…
Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation
Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through con…
RetrievalRetrieval-augmented GenerationArithmetical Binary Decision Tree Traversals
This paper introduces a series of methods for traversing binary decision trees using arithmetic operations. We present a suite of binary tree traversal algorithms that leverage novel representation matrices to flatten th…
Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models
Recent advances in large language models (LLMs) have significantly impacted the domain of multi-hop question answering (MHQA), where systems are required to aggregate information and infer answers from disparate pieces o…
Multi-hop Question AnsweringQuestion AnsweringZero-shot Object Navigation with Vision-Language Models Reasoning
Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, all…
Decision MakingLanguage ModelingLanguage ModellingObject+1