Integrating Large Language Models and Knowledge Graphs for Improved Reasoning and Question Answering
The Observation-Driven Agent (ODA) framework effectively integrates the capabilities of large language models (LLMs) and knowledge graphs (KGs) to enhance reasoning and question-answering performance on KG-centric tasks.
Towards Transferable Foundation Models for Knowledge Graph Reasoning
A method for learning universal and transferable graph representations, ULTRA, that enables zero-shot inference on any knowledge graph with arbitrary entity and relation vocabularies.
Understanding the Expressivity of Graph Neural Networks in Learning Logical Rules for Knowledge Graph Reasoning
Graph Neural Networks (GNNs) with tail entity scoring have achieved state-of-the-art performance on knowledge graph reasoning, but the theoretical understanding of the types of logical rules they can learn is lacking. This paper proposes a unified framework called QL-GNN to analyze the expressivity of these GNNs, formally demonstrating their ability to learn a specific class of rule structures. It further introduces EL-GNN, a novel GNN design that can learn rule structures beyond the capacity of QL-GNN.
Zero-shot Logical Query Answering on Any Knowledge Graph
ULTRAQUERY, a single model that can zero-shot answer complex logical queries on any knowledge graph, even with new entities and relations, by using inductive relation projections and non-parametric logical operators.
Enhancing Complex Logic Query Answering by Integrating Large Language Models and Knowledge Graph Reasoning
The core message of this paper is to propose a novel model called 'Logic-Query-of-Thoughts' (LGOT) that combines the strengths of Large Language Models (LLMs) and knowledge graph reasoning to effectively answer complex logic queries.
Leveraging Large Language Models for Efficient Logical Reasoning over Knowledge Graphs
A novel decoupled approach, Language-guided Abstract Reasoning over Knowledge graphs (LARK), that formulates complex KG reasoning as a combination of contextual KG search and logical query reasoning, to leverage the strengths of graph extraction algorithms and large language models (LLM), respectively.
Query2GMM: Gaussian Mixture Model Representation for Effective Reasoning over Knowledge Graphs
Query2GMM presents a novel query embedding approach that leverages Gaussian Mixture Models to accurately represent multiple disjoint answer subsets for complex logical queries, enabling effective reasoning over knowledge graphs.
