IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0304013.html
   My bibliography  Save this article

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

Author

Listed:
  • Zachary A Pardos
  • Shreya Bhandari

Abstract

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.

Suggested Citation

  • Zachary A Pardos & Shreya Bhandari, 2024. "ChatGPT-generated help produces learning gains equivalent to human tutor-authored help on mathematics skills," PLOS ONE, Public Library of Science, vol. 19(5), pages 1-18, May.
    • Handle: RePEc:plo:pone00:0304013
    DOI: 10.1371/journal.pone.0304013
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0304013
    Download Restriction: no
    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0304013&type=printable
    Download Restriction: no
    File URL: https://libkey.io/10.1371/journal.pone.0304013?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Eti Ben Simon & Matthew P. Walker, 2018. "Sleep loss causes social withdrawal and loneliness," Nature Communications, Nature, vol. 9(1), pages 1-9, December.
    2. Takanobu Hirosawa & Yukinori Harada & Masashi Yokose & Tetsu Sakamoto & Ren Kawamura & Taro Shimizu, 2023. "Diagnostic Accuracy of Differential-Diagnosis Lists Generated by Generative Pretrained Transformer 3 Chatbot for Clinical Vignettes with Common Chief Complaints: A Pilot Study," IJERPH, MDPI, vol. 20(4), pages 1-10, February.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Arpan Kumar Kar & P. S. Varsha & Shivakami Rajan, 2023. "Unravelling the Impact of Generative Artificial Intelligence (GAI) in Industrial Applications: A Review of Scientific and Grey Literature," Global Journal of Flexible Systems Management, Springer;Global Institute of Flexible Systems Management, vol. 24(4), pages 659-689, December.
    2. Guilherme R. Guimaraes & Ricardo G. Figueiredo & Caroline Santos Silva & Vanessa Arata & Jean Carlos Z. Contreras & Cristiano M. Gomes & Ricardo B. Tiraboschi & José Bessa Junior, 2024. "Diagnosis in Bytes: Comparing the Diagnostic Accuracy of Google and ChatGPT 3.5 as an Educational Support Tool," IJERPH, MDPI, vol. 21(5), pages 1-11, May.
    3. Xuening Wang & Xianyun Tian & Xuwei Pan & Dongxu Wei & Qi Qi, 2021. "What Happens When People with Depression Gather Online?," IJERPH, MDPI, vol. 18(16), pages 1-12, August.
    4. Hajdu, Tamás, 2024. "Temperature exposure and sleep duration: Evidence from time use surveys," Economics & Human Biology, Elsevier, vol. 54(C).
    5. Uglješa Stankov & Ulrike Gretzel & Miroslav D. Vujičić & Vanja Pavluković & Tamara Jovanović & Milica Solarević & Marija Cimbaljević, 2022. "The pandemic of loneliness: designing smart tourism for combating loneliness," Information Technology & Tourism, Springer, vol. 24(4), pages 439-455, December.
    6. Konstantinos I. Roumeliotis & Nikolaos D. Tselikas, 2023. "ChatGPT and Open-AI Models: A Preliminary Review," Future Internet, MDPI, vol. 15(6), pages 1-24, May.
    7. Sarah Sandmann & Sarah Riepenhausen & Lucas Plagwitz & Julian Varghese, 2024. "Systematic analysis of ChatGPT, Google search and Llama 2 for clinical decision support tasks," Nature Communications, Nature, vol. 15(1), pages 1-8, December.
    8. Sarah M. Ghose & Morgan P. Reid & Natalie D. Dautovich & Joseph M. Dzierzewski, 2022. "Sleep and Social Wellness: Does Current Subjective and Objective Sleep Inform Future Social Well-Being?," IJERPH, MDPI, vol. 19(18), pages 1-12, September.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0304013. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.