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.

翻译：我们的工作表明，在文本上预训练的大语言模型不仅能解决纯数学文字题，还能解决需要基于先验物理知识进行计算和推理的物理文字题。我们收集并标注了首个物理文字题数据集——PhysQA，其中包含超过1000道初中物理文字题（涵盖运动学、质量与密度、力学、热学、电学）。随后我们使用OpenAI的GPT3.5生成这些问题的答案，发现GPT3.5通过零样本学习能自动解决49.3%的问题，通过少样本学习能解决73.2%的问题。该结果表明，通过使用相似问题及其答案作为提示，大语言模型能以接近人类水平解决基础物理文字题。除了解题外，GPT3.5还能归纳问题所涉及的知识点或主题，提供相关解释，并基于输入生成新的物理文字题。我们的工作是首个聚焦于跨类型、跨场景的物理文字题自动求解、解释与生成的研究，并取得了可接受且最先进的准确率。这凸显了大语言模型在中等教育领域进一步应用的潜力。