Translanguaging in generative AI prompting among Vietnamese EFL learners: an exploratory mixed-methods study

Abstract

As generative artificial intelligence (GenAI) tools are increasingly integrated into academic language learning, research has largely focused on AI-generated outputs, with limited attention to how learners design prompts to guide these systems, particularly in multilingual EFL contexts. Adopting a translanguaging perspective, this study investigates how Vietnamese EFL university students draw on their linguistic repertoires when constructing prompts for GenAI-assisted academic English tasks and examines learner-related factors shaping these practices. Using an exploratory mixed-methods design, survey data from 68 students were analysed to examine reported translanguaging strategy use and its predictors, complemented by an analysis of open-ended responses capturing learners’ reflections on multilingual prompting practices. The results indicate that translanguaging is a common and purposeful feature of prompt design, particularly during planning, idea formulation, and iterative refinement. Regression analyses show that attitudes toward translanguaging significantly predicted strategy use, whereas English proficiency, AI confidence, and gender did not. Qualitative findings further reveal that learners used Vietnamese to clarify intentions, evaluate AI-generated outputs, and regulate cognitive and affective demands. Based on these findings, the study introduces transprompting to conceptualise strategic movement across languages during AI prompt design and highlights pedagogical implications for scaffolding multilingual prompt literacy in AI-supported EFL contexts.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.