Raising the Bar: Automating Consistent and Equitable Student Support with LLMs
This program is tentative and subject to change.
Large Language Models (LLMs) can be used to automate many aspects of the educational field. In this paper, we look into the benefits of automating responses to student questions in course discussion forums using our Retrieval-Augmented Generation (RAG)-based LLM pipeline ForumBot. Our research questions are:
RQ1: How do the responses generated by ForumBot compare to those of TAs in terms of level of detail and use of examples? RQ2: How does the tone of responses generated by ForumBot compare to that of TA responses? RQ3: Are responses generated by ForumBot more consistent than those provided by TAs when answering similar student questions?
Our results suggest that ForumBot generates responses with more detail, examples, positive tone, and consistency than TAs. We envision ForumBot being used as a baseline for TAs to build their responses on, reduce response times, and promote equitable feedback for students.