International Journal of New Developments in Education, 2026, 8(7); doi: 10.25236/IJNDE.2026.080705.
Hongxia Li1, Xin Tuo2
1Xi'an Innovation College of Yan'an University, Xi'an, China
2Xi'an Innovation College of Yan'an University, Xi'an, China
This study examines how AI large language models (LLMs) affect second language (L2) writing development from a second language acquisition (SLA) perspective. Drawing on the Input, Noticing, Interaction, and Output Hypotheses and Sociocultural Theory, it investigates whether LLM-mediated instruction supports accuracy, lexical complexity, syntactic variety, coherence, and metalinguistic awareness. A mixed-methods quasi-experimental design involved 82 Chinese EFL undergraduates in an LLM-assisted experimental group (n = 42) and a teacher-feedback control group (n = 40) over 16 weeks. Writing tests were analyzed with t-tests and ANCOVA, while interviews and journals supplied qualitative evidence. Results showed significantly stronger gains in the experimental group (p < .001), especially in accuracy, lexical diversity, and coherence. Learners also reported stronger noticing, richer input, more pushed output, and lower anxiety, though over-reliance, generic feedback, and integrity concerns remained. The study concludes that LLMs can serve as effective SLA mediators within structured, teacher-guided pedagogy.
Large Language Models, Second Language Writing, Second Language Acquisition, SLA Theories, EFL Writing, AI-Assisted Feedback, Writing Development, Sociocultural Theory
Hongxia Li, Xin Tuo. AI Large Language Models and Second Language Writing Development: A SLA Perspective. International Journal of New Developments in Education (2026), Vol. 8, Issue 7: 26-32. https://doi.org/10.25236/IJNDE.2026.080705.
[1] Hyland, K. (2019). The Routledge handbook of second language acquisition and writing. Routledge.
[2] Li, M. (2023). AI large language models in college EFL writing: Effects and challenges. Journal of Higher Education, 44(5), 112–118.
[3] Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
[4] Luo, Y., Zhang, L., & Wang, H. (2025). A systematic review of AI in second language writing education. Digital Studies in Language and Literature, 2(1), 309–332. https://doi.org/10.1515/dsll-2025-0001
[5] Ellis, R. (2023). The study of second language acquisition (3rd ed.). Oxford University Press.
[6] Chen, G. (2023). AI-assisted L2 writing: Practices, perceptions, and SLA implications. Journal of Second Language Writing, 41, 100445. https://doi.org/10.1016/j.jslw.2023.100445
[7] Guo, S., Zhang, Y., & Li, J. (2024). ChatGPT feedback and L2 writing revision quality. Language Learning & Technology, 28(1), 45–68.
[8] Krashen, S. D. (1985). Principles and practice in second language acquisition. Pergamon.
[9] Schmidt, R. (1990). The role of consciousness in second language learning. Applied Linguistics, 11(2), 129–158.
[10] Long, M. H. (1996). The role of the linguistic environment in second language acquisition. In W. C. Ritchie & T. K. Bhatia (Eds.), Handbook of second language acquisition (pp. 413–468). Academic Press.
[11] Swain, M. (1995). Three functions of output in second language learning. In G. Cook & B. Seidlhofer (Eds.), Principles and practice in applied linguistics (pp. 125–144). Oxford University Press.
[12] Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.
[13] Dalgish, S. M., & Smith, B. L. (2019). Automated writing evaluation: Research and practice. The Modern Language Journal, 103(Suppl. 1), 1–7. https://doi.org/10.1111/modl.12573
[14] Chen, H., & Cheng, L. (2023). Automated writing evaluation in L2 writing: A systematic review. Computer Assisted Language Learning, 36(3), 345–372. https://doi.org/10.1080/09588221.2022.2098761
[15] Darmawansah, I., Suciati, I., & Wardani, S. (2025). ChatGPT as a pre-writing scaffold for L2 argumentative writing. Digital Studies in Language and Literature, 2(1), 123–145. https://doi.org/10.1515/dsll-2025-0003
[16] Hsu, L., & Tai, J. (2024). Interactive AI feedback for L2 writing development: A mixed-methods study. Journal of Educational Technology & Society, 27(1), 78–95.
[17] Werdiningsih, I., Puspita, A., & Saputra, D. (2024). ChatGPT for conversational writing feedback: Learner perceptions and writing outcomes. TESOL Quarterly, 58(1), 201–228.
[18] Xiao, Y. (2024). LLM-assisted lexical development in EFL writing: A corpus-informed analysis. Journal of English for Academic Purposes, 68, 101350.
[19] Boudouaia, M., Li, Y., & Zhang, L. (2024). Proficiency differences in L2 writing development with AI feedback. Journal of Computer-Assisted Language Learning, 37(2), 189–212. https://doi.org/10.1080/09588221.2023.2234567
[20] Wang, Y., & Zhang, X. (2024). Proficiency-mediated LLM effects on L2 writing quality. System, 120, 103218.
[21] Huang, W., Jia, C., Hew, K. F., & Guo, J. (2024). Ethical use of LLMs in L2 writing education. Journal of Language, Identity, and Education, 23(2), 112–126. https://doi.org/10.1080/15348458.2023.2298765
[22] Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa