Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering

TL;DR

This paper demonstrates that using knowledge graphs generated by large language models to decompose physics questions improves the logical consistency and quality of sub-questions, enhancing educational question answering systems.

Contribution

Introduces a novel pipeline leveraging LLM-generated knowledge graphs for better decomposition of physics questions into sub-questions.

Findings

Knowledge graphs improve sub-question fidelity

Enhanced logical consistency in question decomposition

Potential to transform educational content creation

Abstract

This study explores the effectiveness of using knowledge graphs generated by large language models to decompose high school-level physics questions into sub-questions. We introduce a pipeline aimed at enhancing model response quality for Question Answering tasks. By employing LLMs to construct knowledge graphs that capture the internal logic of the questions, these graphs then guide the generation of subquestions. We hypothesize that this method yields sub-questions that are more logically consistent with the original questions compared to traditional decomposition techniques. Our results show that sub-questions derived from knowledge graphs exhibit significantly improved fidelity to the original question's logic. This approach not only enhances the learning experience by providing clearer and more contextually appropriate sub-questions but also highlights the potential of LLMs to transform educational methodologies. The findings indicate a promising direction for applying AI to improve the quality and effectiveness of educational content.