Guided GenAI Use in EFL Poetry Writing: Multimodal Literacy and Learner Agency

Kim, Rakhun

doi:10.30961/lr.2026.62.2.265

Lang. Res. 2026; 62(2):265-302

pISSN: 0254-4474, eISSN: 2586-7113

DOI: https://doi.org/10.30961/lr.2026.62.2.265

Article

Guided GenAI Use in EFL Poetry Writing: Multimodal Literacy and Learner Agency

Rakhun Kim ¹ ^, ^†

Author Information & Copyright ▼

¹Hongik University

^†Corresponding author : E-mail: kimrhee02@hongik.ac.kr

ⓒ Copyright 2026 Language Education Institute, Seoul National University. This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Received: Jul 15, 2026 ; Revised: Aug 15, 2026 ; Accepted: Aug 15, 2026

Published Online: Aug 31, 2026

ABSTRACT

Prior research has raised concerns that generative AI (GenAI) may encourage learner passivity, although most studies have examined its unmediated use. To fill this gap, this exploratory comparative mixed-methods study examined Korean high school students’ engagement with GenAI in guided and unguided poetry writing. Two intact classes received the same instruction in poetic form; only the guided class received multimodal-literacy and learner-agency instruction. A task-specific 12-item self-report questionnaire was administered at pretest, immediate posttest, and four-week delayed posttest. Guided learners’ revisions were analyzed using a perceive–select–act–reflect framework. Mixed ANOVAs showed time-by-condition interactions: the guided class reported a larger increase in agency than the comparison class and remained above pretest at delayed posttest. Qualitatively, all guided learners modified AI-generated texts and explained revision decisions, although rationales varied in specificity, technical precision, and correspondence with revisions. Findings document contrasting self-reported trajectories across classes and selective GenAI engagement in the guided class, without establishing causal instructional effects.

Keywords: GenAI; learner agency; multimodal literacy; EFL writing; poetry writing

References

1..

Attridge, D. (1995). Poetic rhythm: An introduction. Cambridge: Cambridge University Press.

2..

Bastani, H., Bastani, O., Sungu, A., Ge, H., Kabakcı, Ö., & Mariman, R. (2025). Generative AI without guardrails can harm learning: Evidence from high school mathematics. Proceedings of the National Academy of Sciences, 122(26), e2422633122. https://doi.org/10.1073/pnas.2422633122.

3..

Bok, E., & Cho, Y. (2023). Examining Korean EFL college students’ experiences and perceptions of using ChatGPT as a writing revision tool. Journal of English Teaching through Movies and Media, 24(4), 15-27. https://doi.org/10.16875/stem.2023.24.4.15.

4..

Chung, Y. H., & Ahn, B. K. (2025). Metacognitive strategy use in AI-assisted writing: A mixed-methods study of EFL college students’ dialogues with ChatGPT. Studies in English Education, 30(2), 29-56. https://doi.org/10.22275/SEE.30.2.02.

5..

Cook, G. (1997). Language play, language learning. ELT Journal, 51(3), 224-231. https://doi.org/10.1093/elt/51.3.224.

6..

Dillon, T. (2024). Korean university students’ prompt literacy training with ChatGPT: Investigating language learning strategies. English Teaching, 79(3), 123-157. https://doi.org/10.15858/engtea.79.3.202409.123.

7..

Fan, Y., Tang, L., Le, H., Shen, K., Tan, S., Zhao, Y., Shen, Y., Li, X., & Gašević, D. (2025). Beware of metacognitive laziness: Effects of generative artificial intelligence on learning motivation, processes, and performance. British Journal of Educational Technology, 56(2), 489-530. https://doi.org/10.1111/bjet.13544.

8..

Hanauer, D. I. (2012). Meaningful literacy: Writing poetry in the language classroom. Language Teaching, 45(1), 105-115. https://doi.org/10.1017/S0261444810000522.

9..

Hwang, M., Jeens, R., & Lee, H.-K. (2025). Exploring learner prompting behavior and its effect on ChatGPT-assisted English writing revision. The Asia-Pacific Education Researcher, 34(3), 1157-1167. https://doi.org/10.1007/s40299-024-00930-6.

10..

Hwangbo, E., & Bae, J. (2024). The impacts of creating English picture books using generative AI on English reading and writing skills, AI literacy, and self-efficacy of Korean high school students [In Korean]. English Teaching, 79(4), 79-98. https://doi.org/10.15858/engtea.79.4.202412.79.

11..

Jewitt, C., & Kress, G. (Eds.). (2003). Multimodal literacy. New York: Peter Lang.

12..

Jiang, L. (2017). The affordances of digital multimodal composing for EFL learning. ELT Journal, 71(4), 413-422. https://doi.org/10.1093/elt/ccw098.

13..

Jiang, L., & Lai, C. (2025). How did the generative artificial intelligence-assisted digital multimodal composing process facilitate the production of quality digital multimodal compositions: Toward a process-genre integrated model. TESOL Quarterly, 59(S1), S52-S85. https://doi.org/10.1002/tesq.3390.

14..

Jin, F., Lin, C.-H., & Lai, C. (2025). Modeling AI-assisted writing: How self-regulated learning influences writing outcomes. Computers in Human Behavior, 165, 108538. https://doi.org/10.1016/j.chb.2024.108538.

15..

Jin, Y., Yang, K., Martinez-Maldonado, R., Gašević, D., & Yan, L. (2026). The agency gap in AI-supported writing: How reactive and proactive agent designs shape multimodal reasoning. Computers and Education: Artificial Intelligence, 11, 100655. https://doi.org/10.1016/j.caeai.2026.100655.

16..

Kang, J., & Yi, Y. (2023). Beyond ChatGPT: Multimodal generative AI for L2 writers. Journal of Second Language Writing, 62, 101070. https://doi.org/10.1016/j.jslw.2023.101070.

17..

Koltovskaia, S., Rahmati, P., & Saeli, H. (2024). Graduate students’ use of ChatGPT for academic text revision: Behavioral, cognitive, and affective engagement. Journal of Second Language Writing, 65, 101130. https://doi.org/10.1016/j.jslw.2024.101130.

18..

Kosmyna, N., Hauptmann, E., Yuan, Y. T., Situ, J., Liao, X.-H., Beresnitzky, A. V., Braunstein, I., & Maes, P. (2025). Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant for essay writing task (arXiv preprint). https://doi.org/10.48550/arXiv.2506.08872.

19..

Kress, G. (2010). Multimodality: A social semiotic approach to contemporary communication. Oxon and New York: Routledge.

20..

Kress, G., & van Leeuwen, T. (1996). Reading images: The grammar of visual design. London: Routledge.

21..

Kress, G., & van Leeuwen, T. (2001). Multimodal discourse: The modes and media of contemporary communication. London: Arnold.

22..

Kultas, E. (2026). Integration of artificial intelligence into primary school classrooms: The role of ChatGPT in improving poetry writing skills and attitudes towards poetry. BMC Psychology, 14, 1086. https://doi.org/10.1186/s40359-026-04844-4.

23..

Lee, J.-Y. (2025). A meta-analysis of ChatGPT’s effects on English writing in Korean classrooms. English Teaching, 80(5), 175-193. https://doi.org/10.15858/engtea.80.5.202512.175.

24..

Lee, Y. J., & Davis, R. O. (2024). A case study of implementing ChatGPT for university’s general English courses: Focusing on English language learners’ self-regulated learning and grit. Secondary English Education, 17(3), 73-87. https://doi.org/10.20487/kasee.17.3.202406.73.

25..

Li, B., Tan, Y. L., Wang, C., & Lowell, V. (2025). Two years of innovation: A systematic review of empirical generative AI research in language learning and teaching. Computers and Education: Artificial Intelligence, 9, 100445. https://doi.org/10.1016/j.caeai.2025.100445.

26..

Lim, F. V., Toh, W., & Nguyen, T. T. H. (2022). Multimodality in the English language classroom: A systematic review of literature. Linguistics and Education, 69, 101048. https://doi.org/10.1016/j.linged.2022.101048.

27..

Mercer, S. (2011). Understanding learner agency as a complex dynamic system. System, 39(4), 427-436. https://doi.org/10.1016/j.system.2011.08.001.

28..

Michel, M., Bazhutkina, I., Abel, N., & Strobl, C. (2025). Collaborative writing based on generative AI models: Revision and deliberation processes in German as a foreign language. Journal of Second Language Writing, 67, 101185. https://doi.org/10.1016/j.jslw.2025.101185.

29..

Ministry of Education. (2022). 2022 revised national curriculum for English [In Korean]. Sejong: Ministry of Education of Korea.

30..

New London Group. (1996). A pedagogy of multiliteracies: Designing social futures. Harvard Educational Review, 66(1), 60-92. https://doi.org/10.17763/haer.66.1.17370n67v22j160u.

31..

Newfield, D., & d'Abdon, R. (2015). Reconceptualising poetry as a multimodal genre. TESOL Quarterly, 49(3), 510-532. https://doi.org/10.1002/tesq.239.

32..

Park, E. (2025). Multimodal composing in Korean EFL contexts: A systematic literature review [In Korean]. Secondary English Education, 18(5), 79-104. https://doi.org/10.20487/kasee.18.5.202510.79.

33..

Park, H. (2024). ChatGPT-integrated English writing: Writing strategies and perceptions. The Linguistic Association of Korea Journal, 32(3), 85-103. https://doi.org/10.24303/lakdoi.2024.32.3.85.

34..

Seo, J.-Y. (2024). Exploring the educational potential of ChatGPT: AI-assisted narrative writing for EFL college students. Language Teaching Research Quarterly, 43, 1-21. https://doi.org/10.32038/ltrq.2024.43.01.

35..

Song, C., & Song, Y. (2023). Enhancing academic writing skills and motivation: Assessing the efficacy of ChatGPT in AI-assisted language learning for EFL students. Frontiers in Psychology, 14, 1260843. https://doi.org/10.3389/fpsyg.2023.1260843.

36..

Swain, M. (1995). Three functions of output in second language learning. In G. Cook & B. Seidlhofer (Eds.), Principle and practice in applied linguistics: Studies in Honour of H. G. Widdowson (pp. 125-144). Oxford: Oxford University Press..

37..

Towndrow, P. A., Nelson, M. E., & Yusuf, W. F. B. M. (2013). Squaring literacy assessment with multimodal design: An analytic case for semiotic awareness. Journal of Literacy Research, 45(4), 327-355. https://doi.org/10.1177/1086296X13504155.

38..

van Leeuwen, T. (1999). Speech, music, sound. London: Macmillan. https://doi.org/10.1007/978-1-349-27700-1.

39..

van Leeuwen, T. (2006). Towards a semiotics of typography. Information Design Journal, 14(2), 139-155. https://doi.org/10.1075/idj.14.2.06lee.

40..

van Lier, L. (2000). From input to affordance: Social-interactive learning from an ecological perspective. In J. P. Lantolf (Ed.), Sociocultural theory and second language learning (pp. 245-259). Oxford: Oxford University Press.

41..

van Lier, L. (2004). The ecology and semiotics of language learning: A sociocultural perspective. Boston: Kluwer Academic Publishers. https://doi.org/10.1007/1-4020-7912-5.

42..

van Lier, L. (2008). Agency in the classroom. In J. P. Lantolf & M. E. Poehner (Eds.), Sociocultural theory and the teaching of second languages (pp. 163-186). London: Equinox.

43..

Wang, Y. (2024). Cognitive and sociocultural dynamics of self-regulated use of machine translation and generative AI tools in academic EFL writing. System, 126, 103505. https://doi.org/10.1016/j.system.2024.103505.

44..

Yang, I. (2024). A study on poetry writing using ChatGPT: Focusing on user perception and educational approaches [In Korean]. The Journal of Learner-Centered Curriculum and Instruction, 24(6), 619-634. https://doi.org/10.22251/jlcci.2024.24.6.619.

45..

Zimmerman, B. J. (2000). Attaining self-regulation: A social cognitive perspective. In M. Boekaerts, P. R. Pintrich, & M. Zeidner (Eds.), Handbook of self-regulation (pp. 13-39). San Diego: Academic Press. https://doi.org/10.1016/B978-012109890-2/50031-7.