Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning
This is an incremental position paper that highlights problems for educators and developers seeking to use LLMs to enhance students' mathematical problem-solving skills.
The paper identifies challenges in using large language models (LLMs) for mathematics education, such as generating incorrect reasoning and misinterpreting questions, and formulates research questions to address these issues.
Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.