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

TL;DR

This paper demonstrates that large language models like GPT-3.5 can solve, explain, and generate physics word problems with performance nearing human levels, using a new dataset and prompting techniques.

Contribution

It introduces PhysQA, the first annotated physics word problem dataset, and shows that GPT-3.5 can solve and explain physics problems with high accuracy using zero-shot and few-shot learning.

Findings

GPT3.5 solves 49.3% of problems zero-shot

GPT3.5 solves 73.2% of problems few-shot

LLMs can generate explanations and new physics problems

Abstract

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.