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

arXiv: https://arxiv.org/abs/2412.05453 · HTML: https://mlsanity.com/paper/2412.05453/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Builds on (most cited first, 7 of 7)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Efficient Prompting Methods for Large Language Models: A Survey](https://mlsanity.com/paper/2404.01077/) (2024)
- [MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting](https://mlsanity.com/paper/2404.08704/) (2024)
- [Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection](https://mlsanity.com/paper/2402.17256/) (2024)
- [Question Answering via Integer Programming over Semi-Structured Knowledge](https://mlsanity.com/paper/1604.06076/) (2016)

## Built on by (most cited first, 2 of 2)

- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation](https://mlsanity.com/paper/2610.00664/) (2026)

## Abstract (arXiv)

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.