Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?

TL;DR

This paper explores how analogies generated by teacher language models can help student models understand scientific concepts and improve their performance in scientific question answering tasks.

Contribution

It introduces a novel approach where teacher-generated analogies are used to enhance student language models' understanding and self-learning capabilities.

Findings

Teacher analogies aid student models in understanding scientific concepts.

Student models can use analogies for self-improvement in question answering.

Free-form analogies are effective in practical AI applications.

Abstract

Analogical reasoning plays a critical role in human cognition, enabling us to understand new concepts by associating them with familiar ones. Previous research in the AI community has mainly focused on identifying and generating analogies and then examining their quality under human evaluation, which overlooks the practical application of these analogies in real-world settings. Inspired by the human education process, in this paper, we propose to investigate how analogies created by teacher language models (LMs) can assist student LMs in understanding scientific concepts, thereby aligning more closely with practical scenarios. Our results suggest that free-form analogies can indeed aid LMs in understanding concepts. Additionally, analogies generated by student LMs can improve their own performance on scientific question answering, demonstrating their capability to use analogies for self-learning new knowledge. Resources are available at https://github.com/siyuyuan/SCUA.