ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills

Shranjeno v:
Bibliografske podrobnosti
izdano v:PLoS One vol. 19, no. 5 (May 2024), p. e0304013
Glavni avtor: Pardos, Zachary A
Drugi avtorji: Bhandari, Shreya
Izdano:
Public Library of Science
Teme:
Online dostop:Citation/Abstract
Full Text
Full Text - PDF
Oznake: Označite
Brez oznak, prvi označite!

MARC

LEADER 00000nab a2200000uu 4500
001 3069289817
003 UK-CbPIL
022 |a 1932-6203 
024 7 |a 10.1371/journal.pone.0304013  |2 doi 
035 |a 3069289817 
045 2 |b d20240501  |b d20240531 
084 |a 174835  |2 nlm 
100 1 |a Pardos, Zachary A 
245 1 |a ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills 
260 |b Public Library of Science  |c May 2024 
513 |a Journal Article 
520 3 |a Authoring of help content within educational technologies is labor intensive, requiring many iterations of content creation, refining, and proofreading. In this paper, we conduct an efficacy evaluation of ChatGPT-generated help using a 3 x 4 study design (N = 274) to compare the learning gains of ChatGPT to human tutor-authored help across four mathematics problem subject areas. Participants are randomly assigned to one of three hint conditions (control, human tutor, or ChatGPT) paired with one of four randomly assigned subject areas (Elementary Algebra, Intermediate Algebra, College Algebra, or Statistics). We find that only the ChatGPT condition produces statistically significant learning gains compared to a no-help control, with no statistically significant differences in gains or time-on-task observed between learners receiving ChatGPT vs human tutor help. Notably, ChatGPT-generated help failed quality checks on 32% of problems. This was, however, reducible to nearly 0% for algebra problems and 13% for statistics problems after applying self-consistency, a “hallucination” mitigation technique for Large Language Models. 
610 4 |a Code.org 
653 |a Statistics 
653 |a Tutoring 
653 |a Textbooks 
653 |a Large language models 
653 |a Chatbots 
653 |a Decision making 
653 |a Algebra 
653 |a Editing 
653 |a Learning 
653 |a Mathematics 
653 |a Statistical analysis 
653 |a Mathematical models 
653 |a Education 
653 |a Colleges & universities 
653 |a Robotics 
653 |a Social 
700 1 |a Bhandari, Shreya 
773 0 |t PLoS One  |g vol. 19, no. 5 (May 2024), p. e0304013 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3069289817/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3069289817/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3069289817/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch