A Knowledge-Component-Based Methodology for Evaluating AI Assistants

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qi, Laryn, Zamfirescu-Pereira, J. D., Kim, Taehan, Hartmann, Björn, DeNero, John, Norouzi, Narges
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911910696321024
author Qi, Laryn
Zamfirescu-Pereira, J. D.
Kim, Taehan
Hartmann, Björn
DeNero, John
Norouzi, Narges
author_facet Qi, Laryn
Zamfirescu-Pereira, J. D.
Kim, Taehan
Hartmann, Björn
DeNero, John
Norouzi, Narges
contents We evaluate an automatic hint generator for CS1 programming assignments powered by GPT-4, a large language model. This system provides natural language guidance about how students can improve their incorrect solutions to short programming exercises. A hint can be requested each time a student fails a test case. Our evaluation addresses three Research Questions: RQ1: Do the hints help students improve their code? RQ2: How effectively do the hints capture problems in student code? RQ3: Are the issues that students resolve the same as the issues addressed in the hints? To address these research questions quantitatively, we identified a set of fine-grained knowledge components and determined which ones apply to each exercise, incorrect solution, and generated hint. Comparing data from two large CS1 offerings, we found that access to the hints helps students to address problems with their code more quickly, that hints are able to consistently capture the most pressing errors in students' code, and that hints that address a few issues at once rather than a single bug are more likely to lead to direct student progress.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05603
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Knowledge-Component-Based Methodology for Evaluating AI Assistants
Qi, Laryn
Zamfirescu-Pereira, J. D.
Kim, Taehan
Hartmann, Björn
DeNero, John
Norouzi, Narges
Computers and Society
Artificial Intelligence
We evaluate an automatic hint generator for CS1 programming assignments powered by GPT-4, a large language model. This system provides natural language guidance about how students can improve their incorrect solutions to short programming exercises. A hint can be requested each time a student fails a test case. Our evaluation addresses three Research Questions: RQ1: Do the hints help students improve their code? RQ2: How effectively do the hints capture problems in student code? RQ3: Are the issues that students resolve the same as the issues addressed in the hints? To address these research questions quantitatively, we identified a set of fine-grained knowledge components and determined which ones apply to each exercise, incorrect solution, and generated hint. Comparing data from two large CS1 offerings, we found that access to the hints helps students to address problems with their code more quickly, that hints are able to consistently capture the most pressing errors in students' code, and that hints that address a few issues at once rather than a single bug are more likely to lead to direct student progress.
title A Knowledge-Component-Based Methodology for Evaluating AI Assistants
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2406.05603