A PILOT STUDY ON THE IMPACT OF LLMS ON VIRTUAL TUTORING FOR LOW- TO MIDDLE-INCOME COUNTRIES

Nguyen Tien Dat, Phi Van Nguyen, Viet Anh Ngo, Long Tri Thai Son, Nguyen Nhat Minh, Long Q. Tran

Track: Tiny paper

Keywords: large language models, education

TL;DR: This paper evaluates the feasibility of several large language models for tutoring and learning support in Vietnamese.

Abstract: Large Language Models (LLMs) demonstrate increasing proficiency in solving complex tasks and explaining scientific concepts, positioning them as potential tools for democratizing access to personalized education. In low- and middle-income countries, students in rural regions often lack access to high-quality tutoring due to high costs and limited human resources, while the impact of LLMs for this setting is underexplored. To address this gap, we present a pilot study exploring the feasibility of LLMs as personalized tutors for Vietnamese K–12 students preparing for university entrance exams with 540 yes/no questions and focusing on three core STEM subjects: mathematics, physics, and chemistry. Preliminary results indicate both potential benefits and challenges of implementing LLM-driven tutoring systems in resource-constrained educational environments.

Submission Number: 22