# Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level

arXiv: https://arxiv.org/abs/2309.08182 · HTML: https://mlsanity.com/paper/2309.08182/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [MathPrompter: Mathematical Reasoning using Large Language Models](https://mlsanity.com/paper/2303.05398/) (2023)
- [GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning](https://mlsanity.com/paper/2105.14517/) (2021)
- [A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level](https://mlsanity.com/paper/2112.15594/) (2021)
- [Translating a Math Word Problem to an Expression Tree](https://mlsanity.com/paper/1811.05632/) (2018)
- [The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers](https://mlsanity.com/paper/1808.07290/) (2018)
- [LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning](https://mlsanity.com/paper/2205.08232/) (2022)

## Built on by (most cited first, 16 of 16)

- [UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models](https://mlsanity.com/paper/2502.00334/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education](https://mlsanity.com/paper/2410.11123/) (2024)
- [PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems](https://mlsanity.com/paper/2508.00079/) (2025)
- [FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models](https://mlsanity.com/paper/2401.10744/) (2024)
- [SimLM: Can Language Models Infer Parameters of Physical Systems?](https://mlsanity.com/paper/2312.14215/) (2023)
- [Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning](https://mlsanity.com/paper/2504.01911/) (2025)
- [PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models](https://mlsanity.com/paper/2505.24823/) (2025)
- [CueTip: An Interactive and Explainable Physics-aware Pool Assistant](https://mlsanity.com/paper/2501.18291/) (2025)
- [PhysProver: Advancing Automatic Theorem Proving for Physics](https://mlsanity.com/paper/2601.15737/) (2026)
- [xInv: Explainable Optimization of Inverse Problems](https://mlsanity.com/paper/2506.11056/) (2025)
- [Agentic Retrieval and Reinforcement Learned Equation Chains: A Controlled Generation Framework for Complex and Novel Physics Word Problems](https://mlsanity.com/paper/2606.15591/) (2026)
- [Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models](https://mlsanity.com/paper/2607.05199/) (2026)
- [FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening](https://mlsanity.com/paper/2607.05201/) (2026)
- [OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora](https://mlsanity.com/paper/2608.25398/) (2026)
- [New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models](https://mlsanity.com/paper/2609.11022/) (2026)

## Abstract (arXiv)

Our work demonstrates that large language model (LLM) pre-trained on texts can not only solve pure math word problems, but also physics word problems, whose solution requires calculation and inference based on prior physical knowledge. We collect and annotate the first physics word problem dataset-PhysQA, which contains over 1000 junior high school physics word problems (covering Kinematics, Mass&Density, Mechanics, Heat, Electricity). Then we use OpenAI' s GPT3.5 to generate the answer of these problems and found that GPT3.5 could automatically solve 49.3% of the problems through zero-shot learning and 73.2% through few-shot learning. This result demonstrates that by using similar problems and their answers as prompt, LLM could solve elementary physics word problems approaching human level performance. In addition to solving problems, GPT3.5 can also summarize the knowledge or topics covered by the problems, provide relevant explanations, and generate new physics word problems based on the input. Our work is the first research to focus on the automatic solving, explanation, and generation of physics word problems across various types and scenarios, and we achieve an acceptable and state-of-the-art accuracy. This underscores the potential of LLMs for further applications in secondary education.