Volume 30 Number 1, 2026 Custom GPT as mediator: Dynamic Assessment with beginner KFL learners

Custom GPT as mediator: Dynamic Assessment with beginner KFL learners

Repository record updated on:
Feb. 21, 2026, 1:05 p.m.
Database record updated on:
Feb. 23, 2026, 8:25 p.m.
Last Harvested on:
Feb. 23, 2026, 8:25 p.m.
access-status:
open.access
bitstream:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/5094fe5f-45e5-426f-923e-c7d817884d70/download', '30_01_10125-73669.pdf']]
bitstream_txt:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/f71dc2a2-39a8-4f5f-8344-5d3c438cab56/download', 'full_text']]
collection:
Volume 30 Number 1, 2026
contributor.author:
Kim, Minjin
date.accessioned:
2026-02-20T19:34:23Z
date.available:
2026-02-20T19:34:23Z
date.copyright:
2026
date.issued:
2026-02-23
description.abstract:
This study examines how a custom GPT-based chatbot can mediate learner development within the Zone of Proximal Development (ZPD) through dynamic assessment (DA) with beginner-level learners of Korean as a Foreign Language. The model was fine-tuned using OpenAI’s My GPT platform, with a custom prompt specifying graduated mediation, responsive behavior guidelines, and target grammar points. Specifically, the study investigates how GPT operationalizes scaffolding processes in text-based dialogue by sustaining interaction, providing form-focused feedback, and adjusting support contingent on learner responsiveness. Ten English-speaking students in a Korean course at a U.S. university interacted with the chatbot weekly over four weeks. Qualitative analysis of 280 learner-GPT turns identified three mediation types: conversational, instructional, and developmental. Through these, the chatbot maintained natural and level-appropriate dialogue, delivered graduated mediation aligned with learner responsiveness, and used accurate learner responses as springboards to guide movement from the Zone of Actual Development toward the ZPD. Complementary quantitative measures showed higher uptake rates and significant gains in mean length of sentence and lexical diversity. These findings suggest that large language models, when carefully tuned, can emulate core principles of Vygotskian mediation and foster human-AI co-construction of learning within scaffolded interaction.
endingpage:
27
format.extent:
27
identifier.citation:
Kim, M. (2026). Custom GPT as mediator: Dynamic Assessment with beginner KFL learners. Language Learning & Technology, 30(1), 1–27. https://doi.org/10.64152/10125/73669
identifier.doi:
https://doi.org/10.64152/10125/73669
identifier.issn:
1094-3501
identifier.uri:
https://hdl.handle.net/10125/73669
language:
eng
number:
1
publicationname:
Language Learning & Technology
publisher:
University of Hawaii National Foreign Language Resource Center Center for Language & Technology
rights.license:
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
rights.uri:
https://creativecommons.org/licenses/by-nc-nd/4.0/
site_url:
/item/10125-73669/
startingpage:
1
subject:
dynamic assessment, GPT, Korean as a Foreign Language, AI-assisted language learning
title:
Custom GPT as mediator: Dynamic Assessment with beginner KFL learners
type:
Article Text
volume:
30