Understanding EFL Learners' Code-Switching and Teachers' Pedagogical Approaches in LLM-Supported Speaking Practice

2025-12-28

AI Summary

This study investigates the cognitive and affective functions of code-switching (CSW) among Korean L1 EFL learners during LLM-supported speaking practice, and its implications for teacher response strategies. Employing a six-week mixed-methods design—comprising spoken task experiments and in-depth teacher interviews—the research reveals that CSW serves dual purposes: mitigating speaking anxiety and compensating for lexical gaps, while also functioning as a vehicle for cultural and emotional expression. Innovatively integrating teachers’ professional judgment into LLM pedagogical design, the study proposes a “dynamic scaffolding–selective intervention” bilingual tutor framework, elevating CSW from a communicative compensation strategy to a pedagogical opportunity. Findings empirically validate CSW’s positive cognitive and affective value, yield a transferable set of teacher response strategies, and formulate six embodied design principles for bilingual LLM tutors.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

For English as a Foreign Language (EFL) learners, code-switching (CSW), or alternating between their native language and the target language (English), can lower anxiety and ease communication barriers. Large language models (LLMs), with their multilingual abilities, offer new opportunities to support CSW in speaking practice. Yet, the pedagogical design of LLM-based tutors remains underexplored. To this end, we conducted a six-week study of LLM-mediated speaking practice with 20 Korean EFL learners, alongside a qualitative study with nine English teachers who designed and refined responses to learner CSW. Findings show that learners used CSW not only to bridge lexical gaps but also to express cultural and emotional nuance, prompting teachers to employ selective interventions and dynamic scaffolding strategies. We conclude with design implications for bilingual LLM-powered tutors that leverage teachers' expertise to transform CSW into meaningful learning opportunities.

Problem

• Explores EFL learners' code-switching in LLM-supported speaking practice
• Investigates teachers' pedagogical approaches to manage learner code-switching
• Designs bilingual LLM tutors leveraging teacher expertise for learning opportunities

Innovation

• LLM-based bilingual tutors support code-switching in speaking practice
• Teachers use selective interventions and dynamic scaffolding strategies
• Design leverages teacher expertise to transform code-switching into learning