ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots

TL;DR

This paper compares conversational AI models like ChatGPT with traditional question-answering systems for knowledge graphs, evaluating their strengths and limitations, and explores future research directions for integrated KG chatbots.

Contribution

It provides a comprehensive comparison of ChatGPT, Galactica, and KGQAN on multiple knowledge graphs, highlighting current limitations and proposing future research opportunities.

Findings

ChatGPT and Galactica excel in conversational aspects but lack up-to-date KG retrieval.

KGQAN provides accurate retrieval but less conversational interaction.

Identified key challenges and open research directions for KG chatbot development.

Abstract

Conversational AI and Question-Answering systems (QASs) for knowledge graphs (KGs) are both emerging research areas: they empower users with natural language interfaces for extracting information easily and effectively. Conversational AI simulates conversations with humans; however, it is limited by the data captured in the training datasets. In contrast, QASs retrieve the most recent information from a KG by understanding and translating the natural language question into a formal query supported by the database engine. In this paper, we present a comprehensive study of the characteristics of the existing alternatives towards combining both worlds into novel KG chatbots. Our framework compares two representative conversational models, ChatGPT and Galactica, against KGQAN, the current state-of-the-art QAS. We conduct a thorough evaluation using four real KGs across various application domains to identify the current limitations of each category of systems. Based on our findings, we propose open research opportunities to empower QASs with chatbot capabilities for KGs. All benchmarks and all raw results are available1 for further analysis.