Date
Publisher
arXiv
Large language models exhibit superior capabilities in processing and
understanding language, yet their applications in educational contexts remain
underexplored. Learnersourcing enhances learning by engaging students in
creating their own educational content. When learnersourcing multiple-choice
questions, creating explanations for the solution of a question is a crucial
step; it helps other students understand the solution and promotes a deeper
understanding of related concepts. However, it is often difficult for students
to craft effective solution explanations, due to limited subject understanding.
To help scaffold the task of automated explanation generation, we present and
evaluate a framework called "ILearner-LLM", that iteratively enhances the
generated explanations for the given questions with large language models.
Comprising an explanation generation model and an explanation evaluation model,
the framework generates high-quality student-aligned explanations by
iteratively feeding the quality rating score from the evaluation model back
into the instruction prompt of the explanation generation model. Experimental
results demonstrate the effectiveness of our ILearner-LLM on LLaMA2-13B and
GPT-4 to generate higher quality explanations that are closer to those written
by students on five PeerWise datasets. Our findings represent a promising path
to enrich the learnersourcing experience for students and to enhance the
capabilities of large language models for educational applications.
Study at a glance
- Question: Can AI improve explanations for student-created multiple-choice questions by repeatedly refining them based on feedback?
- Setting and data: Five PeerWise datasets.
- Method: Tests an AI framework (ILearner-LLM) that iteratively refines question explanations across two language models.
Why it matters
When students create multiple-choice questions, crafting effective solution explanations is often difficult due to limited subject understanding. Meanwhile, large language model applications in educational contexts remain underexplored.
Key findings
- Across five student question datasets, an iterative AI system generated higher-quality multiple-choice explanations that closely matched student writing.
- Repeatedly incorporating automated quality scores helped language models generate explanations that were better aligned with students.
- Students often struggle to write effective solution explanations for multiple-choice questions due to limited subject understanding.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
