Decomposed Prompting to Answer Questions on a Course Discussion Board
arXiv:2407.21170 · doi:10.1007/978-3-031-36336-8_33
Abstract
We propose and evaluate a question-answering system that uses decomposed prompting to classify and answer student questions on a course discussion board. Our system uses a large language model (LLM) to classify questions into one of four types: conceptual, homework, logistics, and not answerable. This enables us to employ a different strategy for answering questions that fall under different types. Using a variant of GPT-3, we achieve classification accuracy. We discuss our system's performance on answering conceptual questions from a machine learning course and various failure modes.
6 pages. Published at International Conference on Artificial Intelligence in Education 2023. Code repository: https://github.com/brandonjaipersaud/piazza-qabot-gpt