LLM-powered Heterogeneous Information Network Analytics

Abstract

Most existing Knowledge Base Question Answering methods focus primarily on retrieving factual information, leaving more complex, analysis-driven tasks relatively unexplored. However, real-world queries often involve graph-based computations—such as degree calculation or community detection—that require more advanced reasoning. In this paper, we introduce LLM4GraphAna, a Large Language Model-based approach designed to handle these hallenging analysis-focused queries within the KBQA framework. By integrating Function Orchestration and Parameterization, LLM4GraphAna can invoke our well-defined, declarative functions to perform complex graph analyses. Experimental results demonstrate that our method significantly enhances performance on analysis-intensive questions.

Publication
The Web Conference (WWW, short paper)
Date
Links