EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

When does GenAI work for L2 learning? A three‐level meta‐analysis

Zhihui Zhang, Scott Aubrey, Xiuyi Wu, Thomas K. F. Chiu

Review of Education · 2026-12 · 14 (3)

DOI: 10.1002/rev3.70252 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Review of Education, online erschienen am 11.11.2026. Verfasst von Zhihui Zhang und 3 weiteren Autor:innen. Die Arbeit nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This three‐level meta‐analysis examined when generative AI (GenAI) works for second language (L2) learning, synthesizing 67 effect sizes from 48 controlled studies ( N = 5196) published between 2023 and 2026, with a focus on GenAI's text generation and conversational interaction capabilities. GenAI demostrated a large overall effect on measured L2 learning outcomes ( g = 0.76, 95% CI [0.50, 1.02]); after removal of influential outliers, the effect remained significant but was smaller ( g = 0.57). Effects varied by skill domain: speaking showed the largest full‐sample effect ( g = 1.48), which declined substantially after outlier adjustment ( g = 0.65), while vocabulary ( g = 0.66) and writing ( g = 0.61) remained moderate and reading was non‐significant. Regarding integration design, GenAI functioning as a feedback and assessment provider yielded the largest effects (full‐sample g = 1.15; adjusted g = 0.83), and interaction configurations with higher learner agency (Student‐Led, g = 0.92; Co‐Creative, g = 0.82) outperformed AI‐directed ones (AI‐Led, g = 0.34). Teacher role did not significantly moderate effects in the primary analysis; an observer‐teacher advantage ( g = 0.99) emerged only after outlier removal and should be considered exploratory. These findings suggest that GenAI effectiveness depends on instructional configuration, including the functional role assigned to the tool, the learner–AI interaction mode and the nature of teacher involvement, rather than representing an inherent advantage of the technology itself.

Zitieren

APA

Zhang, Z., Aubrey, S., Wu, X., & Chiu, T. K. F. (2026). When does GenAI work for L2 learning? A three‐level meta‐analysis. Review of Education, 14(3). https://doi.org/10.1002/rev3.70252

Vancouver

Zhang Z, Aubrey S, Wu X, Chiu TKF. When does GenAI work for L2 learning? A three‐level meta‐analysis. Review of Education. 2026;14(3). doi:10.1002/rev3.70252

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhihui and Aubrey, Scott and Wu, Xiuyi and Chiu, Thomas K. F.},
  title = {When does GenAI work for L2 learning? A three‐level meta‐analysis},
  journal = {Review of Education},
  year = {2026},
  volume = {14},
  number = {3},
  doi = {10.1002/rev3.70252}
}
Kostenlos starten →