Building and assessing an LLM-based subject-specific intelligent language tutoring system

Research Project

Project/Area Number	25K16371
Research Category	Grant-in-Aid for Early-Career Scientists
Allocation Type	Multi-year Fund
Review Section	Basic Section 02100:Foreign language education-related
Research Institution	Tokyo University of Science
Principal Investigator	HOFMEYR MICHAEL・FREDERICK 東京理科大学, 教養教育研究院葛飾キャンパス教養部, 講師 (70817486)
Project Period (FY)	2025-04-01 – 2028-03-31
Project Status	Granted (Fiscal Year 2025)
Budget Amount *help	¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000) Fiscal Year 2027: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2026: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000) Fiscal Year 2025: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords	AI / language tutoring system / chatbot / ESP
Outline of Research at the Start	An LLM-based ILT system will be created that takes full advantage of the educational affordances that generative artificial intelligence (AI) can provide. The system’s effectiveness will be tested via a mixed-methods experimental study on engineering students completing three different reading tasks. Learners’ usage patterns and perceptions of the ILT system will also be analysed.