KG4QG: combining knowledge graph with large language models for multi-hop question generation

Abstract

Question generation is a task of Natural Language Processing where the goal is to generate fluent, grammatically correct, and error-free questions based on a given input context and optionally an answer. Multi-hop question generation is a more complex task compared to traditional single-hop question generation, as it requires reasoning over multiple information from multiple input contexts in generating multi-hop questions. In our work, we have addressed the challenge of building a multi-hop question generation system by combining the knowledge graphs with Large Language Models (LLMs). We have designed a framework KG4QG(Knowledge Graph for Question Generation), where knowledge graphs are generated from the input contexts. For the knowledge graph embedding, we use a Graph Attention Network, and for input texts embedding, we leverage a Sentence Transformer. Finally, we apply the BART and T5 models as Large Language Models to generate multi-hop questions from our proposed model. Using the HotpotQA dataset to evaluate the performance of our KG4QG framework, our proposed methodology shows enhanced performance over the previous methodologies