How Can Large Language Models Support Learning?
Japanese Language and Literature · 29.10.2026 · 60 (2)
DOI: 10.5195/jll.2026.480 ↗Kurz gefasst
Fachartikel in der Zeitschrift Japanese Language and Literature, online erschienen am 29.10.2026. Verfasst von Ariel Stilerman und 12 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We discuss a novel approach to Premodern Japanese Language Pedagogy (PJLP) with potential applications in other languages and fields. Drawing inspiration from grassroots initiatives such as the DIY and Maker movements, this paper advocates for an approach to AI in Education that fosters instructional and student agency over the pedagogical process. Specifically, we discuss a tutoring framework for textual analysis in the context of a graduate seminar in premodern Japanese literature, as well as a bilingual interactive dictionary and a conversational partner created for a language course in Classical Japanese. Created through prompt engineering as custom instances of a Large Language Model (LLM), these three tools are designed to counteract the tendency of out-of-the-box LLMs to either bypass student effort through over-explanation or misguide learners via hallucinations. To illustrate how this approach can promote active comprehension and pedagogical alignment, we provide transcripts (logs) of actual exchanges, sample instructions (system prompts), and guidance for instructors curious about exploring this approach in a variety of fields (starter kit).
Zitieren
APA
Stilerman, A., Nelson, A., Cheng, A., Langley, C., Wang, S., Piana, C., Çılgın, P., Qin, Q., Nishimitsu, T., Zhang, L., Liu, H., Eyre, J., & Sherry, G. (2026). How Can Large Language Models Support Learning?. Japanese Language and Literature, 60(2). https://doi.org/10.5195/jll.2026.480
Vancouver
Stilerman A, Nelson A, Cheng A, Langley C, Wang S, Piana C, et al. How Can Large Language Models Support Learning?. Japanese Language and Literature. 2026;60(2). doi:10.5195/jll.2026.480
BibTeX
@article{Stilerman2026,
author = {Stilerman, Ariel and Nelson, Andrew and Cheng, Alan and Langley, Caleb and Wang, Sera and Piana, Camilla and Çılgın, Pelin and Qin, Qianhe and Nishimitsu, Teisha and Zhang, Liaoliao and Liu, Huiting and Eyre, Josh and Sherry, Gavin},
title = {How Can Large Language Models Support Learning?},
journal = {Japanese Language and Literature},
year = {2026},
volume = {60},
number = {2},
doi = {10.5195/jll.2026.480}
}
EUVIMED