Roles of Generative Artificial Intelligence (GenAI) in English as a Foreign Language (EFL) Instruction: A Systematic Literature Review

Despite the growing potential of Generative Artificial Intelligence (GenAI) to enhance learning—particularly in transforming traditional English as a Foreign Language (EFL) teaching and learning practices—there is still limited research available to guide educators and practitioners in understanding its role in pedagogical contexts. This systematic literature review (SLR) explores GenAI’s roles in EFL instruction by examining application contexts, research methods employed, and key issues identified. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), 51 articles from an initial pool of 284 studies published between 2020 and 2024 (based on early access year) were selected from WoS and Scopus. Findings of application contexts revealed the marked preference of higher education settings, particularly in East Asia and the Middle East, with an overwhelming focus on writing instruction. Methodologically, mixed and qualitative methods, large sample sizes, and subjective data prevailed. Furthermore, research issues demonstrated GenAI’s versatile yet double-edged role in specific courses, including writing, reading, speaking, grammar, and general EFL instruction, particularly its role as an assessor. Notably, despite divergent findings on the effectiveness of GenAI in writing instruction, students consistently preferred teacher feedback over GenAI feedback. Moreover, a teacher-centered perspective remained dominant in studies of general EFL instruction. Therefore, future research is encouraged to broaden application contexts, strengthen quantitative approaches with varied sample sizes and objective data, and deepen exploration of the GenAI’s roles in the full teaching cycle, addressing existing divergences and incorporating more perspectives.