Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering
This work addresses the challenge of enhancing educational content quality for high school physics learners, though it appears incremental as it builds on existing decomposition techniques with a novel method.
This study tackled the problem of decomposing high school-level physics questions into sub-questions by using knowledge graphs generated by large language models, resulting in sub-questions with significantly improved fidelity to the original question's logic.
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.