Communications in Humanities Research ISSN: 2753-7072
Home> Volumes> Volume CHR Vol.112> Article
Research Article

The Impact of Generative AI Feedback on Grammar Accuracy and Lexical Richness in L2 Writing

Xinyi QianNanjing Institute of Technology*

* Corresponding author: [email protected]

Abstract

Nowadays, education and teaching assisted by generative artificial intelligence (AI) have become viral. The traditional feedback mechanism adopted in second-language academic writing is mainly the teacher's written corrective feedback (WCF). However, in recent years, AI feedback also provides diversified guidance for second-language writing. Therefore, some scholars have studied the impact of AI feedback on second-language academic writing. This article mainly conducts a systematic review of empirical research in this field. In view of the fact that grammatical accuracy and vocabulary richness in the process of second language writing are the core indicators for judging the quality of writing, and there are many research cases, this article mainly develops from these two dimensions to discuss the promoting role and mechanism of AI feedback. The study shows that AI feedback has significantly improved the language accuracy and vocabulary richness of second-language academic writing, mainly by reducing basic grammatical errors and using synonymous replacements for frequently used words in writing; however, it is also found that AI feedback has problems, such as a lack of context understanding and excessive modification. Therefore, it is still necessary to combine teacher feedback with AI feedback to help learners learn second-language academic writing.

Keywords: Generative AI; Grammar Accuracy; Lexical Richness; L2 Writing
Published: June 8, 2026
DOI: 10.54254/2753-7064/2026.34672
Volume: CHR Vol.112
pp. 1-8
Download PDF

References

  1. Brandmo, C., & Gamlem, S. M. (2025). Students' perceptions and outcome of teacher feedback: A systematic review. Frontiers in Education, 10, 1572950.
  2. Pearson, W. S. (2022). A typology of the characteristics of teachers' written feedback comments on second language writing. Cogent Education, 9(1), 2024937.
  3. Hamzehloo, M., Azar, A. S., & Hamzehloo, M. (2026). Leveraging AI for future-ready writing education. IGI Global.
  4. Ding, L., Zou, D., & Kohnke, L. (2026). Enhancing L2 writing with AI: Effects of ChatGPT feedback and the role of student engagement. Artificial Intelligence in Language Education, 2, 103356.
  5. Muñoz, B. C. M., Nassaji, H., & Carrillo, F. I. B. (2025). ChatGPT-generated versus human direct corrective feedback on L2 writing. System, 134, 103805.
  6. Chen, Q. (2025). Students' perceptions of AI-powered feedback in English writing: Benefits and challenges in higher education. International Journal of Computer-Assisted Education.
  7. Ahmadi, R. (2025). A qualitative investigation of ChatGPT's impact on grammar proficiency in Iranian EFL students' academic writing. Applied Linguistics Compass, 1(3), 65–74.
  8. Mekheimer, M. (2025). Generative AI-assisted feedback and EFL writing: A study on proficiency, revision frequency, and writing quality. Discover Education, 4(1), 170.
  9. Ellis, N. C. (2019). Essentials of a theory of language cognition. The Modern Language Journal, 103, 39–60.
  10. Ji, N. Y. (2020). Effectiveness of AI editing software for corrective feedback in L2 writing. English Language Assessment, 15(2), 31–52.
  11. Sung, H., Csuros, K., & Sung, M. C. (2025). Comparing human and LLM proofreading in L2 writing: Impact on lexical and syntactic features. arXiv. https: //arxiv.org/abs/2506.09021
  12. Xie, L., Li, L. X., Li, H., Yuan, Z., Fang, Z., & Qiao, S. (2026). Developing lexical richness: A longitudinal learner corpus analysis of L2 writing development under AI and teacher written corrective feedback conditions. International Journal of Applied Linguistics.