Saved in:
Bibliographic Details
Main Authors: Jaipersaud, Brandon, Zhang, Paul, Ba, Jimmy, Petersen, Andrew, Zhang, Lisa, Zhang, Michael R.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.21170
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909274880344064
author Jaipersaud, Brandon
Zhang, Paul
Ba, Jimmy
Petersen, Andrew
Zhang, Lisa
Zhang, Michael R.
author_facet Jaipersaud, Brandon
Zhang, Paul
Ba, Jimmy
Petersen, Andrew
Zhang, Lisa
Zhang, Michael R.
contents 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 $81\%$ classification accuracy. We discuss our system's performance on answering conceptual questions from a machine learning course and various failure modes.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21170
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decomposed Prompting to Answer Questions on a Course Discussion Board
Jaipersaud, Brandon
Zhang, Paul
Ba, Jimmy
Petersen, Andrew
Zhang, Lisa
Zhang, Michael R.
Computation and Language
Human-Computer Interaction
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 $81\%$ classification accuracy. We discuss our system's performance on answering conceptual questions from a machine learning course and various failure modes.
title Decomposed Prompting to Answer Questions on a Course Discussion Board
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2407.21170