Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities

TL;DR

This survey reviews methods combining large language models and knowledge graphs for question answering, analyzing their strengths, limitations, and how they address complex QA challenges, while highlighting future opportunities.

Contribution

It introduces a structured taxonomy for synthesizing LLMs and KGs in QA, systematically surveys current methods, and discusses open challenges and future directions.

Findings

Synthesizes recent approaches integrating LLMs and KGs for QA.

Analyzes strengths, limitations, and KG requirements of different methods.

Highlights open challenges and opportunities in the field.

Abstract

Large language models (LLMs) have demonstrated remarkable performance on question-answering (QA) tasks because of their superior capabilities in natural language understanding and generation. However, LLM-based QA struggles with complex QA tasks due to poor reasoning capacity, outdated knowledge, and hallucinations. Several recent works synthesize LLMs and knowledge graphs (KGs) for QA to address the above challenges. In this survey, we propose a new structured taxonomy that categorizes the methodology of synthesizing LLMs and KGs for QA according to the categories of QA and the KG's role when integrating with LLMs. We systematically survey state-of-the-art methods in synthesizing LLMs and KGs for QA and compare and analyze these approaches in terms of strength, limitations, and KG requirements. We then align the approaches with QA and discuss how these approaches address the main challenges of different complex QA. Finally, we summarize the advancements, evaluation metrics, and benchmark datasets and highlight open challenges and opportunities.