Date
Publisher
arXiv
We discuss a novel approach to Premodern Japanese Language Pedagogy (PJLP) with potential applications in other languages and fields. The integration of artificial intelligence into education has largely operated as a top-down project, affording minimal agency to everyday users. This dynamic mirrors the broader frontier model ecosystem, which concentrates massive human and financial resources within a few labs. 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).
Study at a glance
- Question: Can customized prompt engineering create effective AI learning partners that preserve student agency in premodern Japanese language pedagogy?
- Setting and data: Stanford University undergraduate and graduate premodern Japanese literature and language courses, Winter and Spring 2026; student interaction logs and voluntary feedback.
- Method: Design-based development and qualitative testing of custom prompt-engineered AI tools using classroom feedback and interaction logs.
Why it matters
Generic AI platforms tend to bypass student effort through over-explanation or misguide learners through hallucinations. Premodern Japanese language courses require extensive background knowledge, creating steep learning hurdles that top-down AI tools often fail to support effectively.
Key findings
- Prompt-engineered tools using Socratic questioning successfully guided students through step-by-step grammatical analysis and sentence decipherment without directly handing them the answers.
- System prompts allowed the AI tutor to dynamically adapt questioning complexity and explanations between advanced students and beginners without requiring complex rubrics.
- The models showed operational limitations, including degraded performance over long sessions, loss of structural tracking in complex sentences, and occasional assertion of competing interpretations with equal conviction.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
