Abstract
While the role of generative artificial intelligence (GenAI) in English as a foreign language (EFL) writing instruction has received growing research attention, its impact on speaking and pronunciation remains underexplored. This PRISMA-based systematic review examines the challenges associated with using GenAI tools, particularly large language model (LLM)-based chatbots, for EFL speaking and pronunciation practice and synthesizes evidence-based mitigation strategies. Twelve studies that met the eligibility criteria yielded 48 challenges. These were organized into six thematic categories, including technical, pedagogical, learner-related, and equity concerns. The studies also varied in research design and instructional context. Several recurrent patterns emerged across the categories. Output accuracy and reliability represented the most persistent challenge and were linked to concerns about learner trust and uncritical reliance. AI-generated feedback was also repeatedly described as mechanical, formulaic, and lacking contextual sensitivity, highlighting a tension between the accessibility and scalability of these tools and limitations in areas that are important to learners. The studies commonly identified a human-in-the-loop approach as a key mitigation principle, alongside technical improvements and pedagogical interventions, including prompt literacy training. However, important questions remain unresolved, particularly whether GenAI reduces or increases teacher workload and if these tools narrow or widen existing equity gaps. Overall, the findings suggest that effective integration of GenAI into EFL speaking instruction requires attention to technical design, pedagogy, and institutional support, while several aspects of its implementation remain insufficiently understood.
References
[1] N. Abbas, I. Ali, R. Manzoor, T. Hussain, and M. H. AL Hussaini, "Role of artificial intelligence tools in enhancing students' educational performance at higher levels," J. Artif. Intell., Mach. Learn. Neural Netw., vol. 3, no. 5, pp. 36-49, 2023, doi: 10.55529/jaimlnn.35.36.49. (in English).
[2] H. Alisoy, "The impact of AI-powered personalized learning on ESL student outcomes," EuroGlobal J. Linguistics Lang. Educ., vol. 2, no. 2, pp. 89-98, 2025, doi: 10.69760/egjlle.2500187. (in English).
[3] S. Mahapatra, "Impact of ChatGPT on ESL students' academic writing skills: A mixed methods intervention study," Smart Learn. Environ., vol. 11, 2024, Art. no. 9, doi: 10.1186/s40561-024-00295-9. (in English).
[4] M. Mekheimer, "Generative AI-assisted feedback and EFL writing: A study on proficiency, revision frequency and writing quality," Discover Educ., vol. 4, 2025, Art. no. 170, doi: 10.1007/s44217-025-00602-7. (in English).
[5] P. Polakova and P. Ivenz, "The impact of ChatGPT feedback on the development of EFL students' writing skills," Cogent Educ., vol. 11, no. 1, 2024, Art. no. 2410101, doi: 10.1080/2331186X.2024.2410101. (in English).
[6] A. Jankovic and D. Kulic, "Use and misuse of ChatGPT in academic writing among the English language students," Inf. Technol. Learn. Tools, vol. 105, no. 1, pp. 178-188, 2025, doi: 10.33407/itlt.v105i1.5955. (in English).
[7] J. Du and B. K. Daniel, "Transforming language education: A systematic review of AI-powered chatbots for English as a foreign language speaking practice," Comput. Educ. Artif. Intell., vol. 6, 2024, Art. no. 100230, doi: 10.1016/j.caeai.2024.100230. (in English).
[8] B. Li, Y. L. Tan, C. Wang, and V. Lowell, "Two years of innovation: A systematic review of empirical generative AI research in language learning and teaching," Comput. Educ. Artif. Intell., vol. 9, 2025, Art. no. 100445, doi: 10.1016/j.caeai.2025.100445. (in English).
[9] C. K. Lo, P. L. H. Yu, S. Xu, D. T. K. Ng, and M. S. Jong, "Exploring the application of ChatGPT in ESL/EFL education and related research issues: A systematic review of empirical studies," Smart Learn. Environ., vol. 11, 2024, Art. no. 50, doi: 10.1186/s40561-024-00342-5. (in English).
[10] A. Alenezi and A. Alenezi, "The use of artificial intelligence in English learning: Teachers' and students' perceptions," Inf. Technol. Learn. Tools, vol. 108, no. 4, pp. 37-52, 2025, doi: 10.33407/itlt.v108i4.6127. (in English).
[11] I. Xodabande, S. Shiri, and M. Zohrabi, "Exploring the impacts of an AI-driven instructional intervention on Iranian EFL learners' pronunciation skill development," Discover Educ., vol. 4, 2025, Art. no. 307, doi: 10.1007/s44217-025-00782-2. (in English).
[12] FX. Baskara, "Navigating the complexities and potentials of language learning machines in EFL contexts: A multidimensional analysis," in Proc. 4th Int. Conf. Language, Literary, and Cultural Studies (ICON LATERALS), 2023, doi: 10.4108/eai.11-7-2023.2340636. (in English).
[13] M. B. Ulla and M. F. Teng, "Generative artificial intelligence (AI) applications in TESOL: Opportunities, issues, and perspectives [Editorial]," Int. J. TESOL Stud., vol. 6, no. 3, pp. 1-3, 2024, doi: 10.58304/ijts.20240301. (in English).
[14] H. Jiang, "Applications and research gaps of LLM-based English-as-a-foreign-language education," J. Educ. Humanit. Social Sci., vol. 39, pp. 429-434, 2024, doi: 10.54097/jkhv4m38. (in English).
[15] L. Wei, "Artificial intelligence in language instruction: Impact on English learning achievement, L2 motivation, and self-regulated learning," Front. Psychol., vol. 14, 2023, Art. no. 1261955, doi: 10.3389/fpsyg.2023.1261955. (in English).
[16] A. R. Doshi and O. P. Hauser, "Generative AI enhances individual creativity but reduces the collective diversity of novel content," Sci. Adv., vol. 10, no. 28, 2024, doi: 10.1126/sciadv.adn5290. (in English).
[17] J. Liu, A. J. B. Sihes, and Y. Lu, "How do generative artificial intelligence (AI) tools and large language models (LLMs) influence language learners' critical thinking in EFL education? A systematic review," Smart Learn. Environ., vol. 12, 2025, Art. no. 48, doi: 10.1186/s40561-025-00406-0. (in English).
[18] T. Duong and S. Suppasetseree, "The effects of an artificial intelligence voice chatbot on improving Vietnamese undergraduate students' English speaking skills," Int. J. Learn., Teaching Educ. Res., vol. 23, no. 3, pp. 293-321, 2024, doi: 10.26803/ijlter.23.3.15. (in English).
[19] J. Fathi, M. Rahimi, and A. Derakhshan, "Improving EFL learners' speaking skills and willingness to communicate via artificial intelligence-mediated interactions," System, vol. 121, 2024, Art. no. 103254, doi: 10.1016/j.system.2024.103254. (in English).
[20] T.-Y. Tai and H. H.-J. Chen, "Improving elementary EFL speaking skills with generative AI chatbots: Exploring individual and paired interactions," Comput. Educ., vol. 220, 2024, Art. no. 105112, doi: 10.1016/j.compedu.2024.105112. (in English).
[21] W. Choi, "The role of changes in pronunciation ability and anxiety through Gen-AI on EFL learners' self-directed speaking motivation and social interaction confidence: A CHAT perspective," System, vol. 133, 2025, Art. no. 103788, doi: 10.1016/j.system.2025.103788. (in English).
[22] G. P. Georgiou, "Artificial intelligence in pronunciation teaching: Use and beliefs of foreign language teachers," J. Educ. Teach., vol. 52, no. 4, pp. 821-840, 2026, doi: 10.1080/02607476.2026.2676279. (in English).
[23] J. A. Mompean, "ChatGPT for L2 pronunciation teaching and learning," ELT J., vol. 78, no. 4, pp. 423-434, 2024, doi: 10.1093/elt/ccae050. (in English).
[24] A. Matiienko-Silnytska, N. Mikava, I. Savranchuk, N. Tkhor, and H. Poliakova, "Conversational analysis of learner-AI chatbot interactions in developing spoken fluency," Arab World English J., vol. 16, no. 4, pp. 224-238, 2025, doi: 10.24093/awej/vol16no4.13. (in English).
[25] J. Taeza, "The role of AI-powered chatbots in enhancing second language acquisition: An empirical investigation of conversational AI assistants," Edelweiss Appl. Sci. Technol., vol. 9, no. 3, pp. 2616-2629, 2025, doi: 10.55214/25768484.v9i3.5853. (in English).
[26] K. L. R. Chan and J. Liu, "Using multiple GenAI tools in pronunciation teaching: An AI-assisted teaching flowchart in blended learning and flipped learning," J. Educators Online, vol. 22, no. 3, 2025, doi: 10.9743/JEO.2025.22.3.6. (in English).
[27] J. Muniandy and M. Selvanathan, "ChatGPT, a partnering tool to improve ESL learners' speaking skills: Case study in a public university, Malaysia," Teach. Public Admin., vol. 43, no. 1, pp. 4-20, 2025, doi: 10.1177/01447394241230152. (in English).
[28] M. J. Page et al., "The PRISMA 2020 statement: An updated guideline for reporting systematic reviews," BMJ, vol. 372, 2021, Art. no. n71, doi: 10.1136/bmj.n71. (in English).
[29] J. P. T. Higgins et al., Eds., Cochrane handbook for systematic reviews of interventions, version 6.5, updated Aug. 2024. Cochrane, 2024. [Online]. Available: https://www.cochrane.org/authors/handbooks-and-manuals/handbook (in English).
[30] A. Raimkulova, K. Ybyraimzhanov, M. Halmatov, G. Mailybayeva, and Y. Khaimuldanov, "Pre-service EFL primary teachers adopting GenAI-powered game-based instruction: A practicum intervention," Educ. Sci., vol. 15, no. 10, 2025, Art. no. 1326, doi: 10.3390/educsci15101326. (in English).
[31] Z. Li, "Bridging pedagogy and technology: A generative AI and IoT approach to transformative English language education," Humanit. Social Sci. Commun., vol. 12, 2025, Art. no. 1879, doi: 10.1057/s41599-025-06151-6. (in English).
[32] D. Zhang, J. G. Wu, and Z. Fu, "From shy to fly: Facilitating EFL learners' willingness to communicate with an AI chatbot and an intelligent tutoring system," System, vol. 127, 2024, Art. no. 103501, doi: 10.1016/j.system.2024.103501. (in English).
[33] A. M. Mohamed, "Using AI to teach English to multilingual autistic children: A qualitative study," Int. J. Inclusive Educ., vol. 30, no. 9, pp. 2469-2489, 2026, doi: 10.1080/13603116.2025.2564336. (in English).
[34] J. Huang, A. Mizumoto, and Y. L. Huang, "Comparing peer feedback and generative artificial intelligence feedback in Japanese English as a foreign language speaking context: Impacts on motivation, engagement, and writing self-efficacy," Int. J. Appl. Linguistics, vol. 36, no. 2, pp. 1696-1707, 2026, doi: 10.1111/ijal.70020. (in English).
[35] Y. Ling and J. M. Jan, "Voices from the flip: Teacher perspectives on integrating AI chatbots in flipped English classrooms," Educ. Sci., vol. 15, no. 9, 2025, Art. no. 1219, doi: 10.3390/educsci15091219. (in English).
[36] D. Darmawansah, D. Rachman, F. Febiyani, and G.-J. Hwang, "ChatGPT-supported collaborative argumentation: Integrating collaboration script and argument mapping to enhance EFL students' argumentation skills," Educ. Inf. Technol., vol. 30, pp. 3803-3827, 2025, doi: 10.1007/s10639-024-12986-4. (in English).
[37] P.-A. Nguyen, "Evaluating AI-generated language as models for strategic competence in English language teaching," IAFOR J. Educ.: Stud. Educ., vol. 12, no. 3, pp. 325-349, 2024, doi: 10.22492/ije.12.3.13. (in English).
[38] H. Liu, C. Lv, and J. Chen, "Willingness to communicate and anxiety in human-human and human-chatbot interaction contexts: An idiodynamic investigation," Innov. Lang. Learn. Teaching, to be published, doi: 10.1080/17501229.2025.2560101. (in English).
[39] A. M. Almineeai, M. A. Alrashed, T. A. Hezam, A. F. Alharthi, and S. F. Alharthi, "The impact of ChatGPT on EFL medical track students' affective filter," J. Lang. Teaching Res., vol. 16, no. 1, pp. 158-167, 2025, doi: 10.17507/jltr.1601.17. (in English).
[40] W. Juan, H. H. Binti Ismail, and A. Z. Mansor, "Enhancing Chinese EFL learners' speaking proficiency through AI-integrated POA," Educ. Sci.: Theory Pract., vol. 25, no. 2, pp. 44-57, 2025, doi: 10.12738/jestp.2024.2.018. (in English).
[41] D. Song, "How learners' trust changes in generative AI over a semester of undergraduate courses," Int. J. Artif. Intell. Educ., vol. 35, pp. 1445-1464, 2025, doi: 10.1007/s40593-024-00446-6. (in English).
[42] I. P. Y. Laksana, P. D. Hudiananingsih, K. Suciani, P. T. Virginiya, and L. G. E. Wahyuni, "Exploring the possible use of generative artificial intelligence in supporting students' speaking performance," Prosiding Seminar Nasional Riset Bahasa dan Pengajaran Bahasa, vol. 6, no. 1, pp. 208-218, 2024. [Online]. Available: https://ojs2.pnb.ac.id/index.php/SENARILIP/article/view/2219 (in English).
[43] A. Shahini, "Emotional dimensions of feedback: How AI and human responses shape ESL learning outcomes," Ampersand, vol. 15, 2025, Art. no. 100235, doi: 10.1016/j.amper.2025.100235. (in English).
[44] M. Huang and F. Hu, "From comparison to integration: A hybrid feedback model based on student perceptions of AI and teacher support in EFL speaking," Accents Asia, vol. 20, no. 2, pp. 12-35, 2025. [Online]. Available: https://accentsasia.org/issues/20-2/Huang.pdf (in English).
[45] K. Hyland, "EFL teachers and feedback fatigue: AI to the rescue?" Lang. Teaching, vol. 59, no. 3, pp. 310-326, 2026, doi: 10.1017/S0261444825101018. (in English).
[46] S. S. Lee and R. L. Moore, "Harnessing generative AI (GenAI) for automated feedback in higher education: A systematic review," Online Learn., vol. 28, no. 3, pp. 82-104, 2024, doi: 10.24059/olj.v28i3.4593. (in English).
[47] A. Ilma and Z. Rohmah, "AI in EFL education: Teachers' competence and the roadblocks to teaching material development," Cogent Educ., vol. 12, no. 1, 2025, Art. no. 2588471, doi: 10.1080/2331186X.2025.2588471. (in English).
[48] E. Tour and A. Zadorozhnyy, "Conceptualizing and operationalizing prompt literacy for English language learners," J. Adolesc. Adult Literacy, vol. 69, no. 3, 2025, Art. no. e70020, doi: 10.1002/jaal.70020. (in English).
[49] L. Vesna, P. S. Sawale, P. Kaul, S. Pal, and S. N. V. R. M. Banda, “Digital divide in AI-powered education: Challenges and solutions for equitable learning,” J. Inf. Syst. Eng. Manage., vol. 10, no. 21s, pp. 300–308, 2025, doi: 10.52783/jisem.v10i21s.3327. (in English).
[50] Anthropic, “Claude Opus 4.6,” 2026. [Online]. Available: https://www.anthropic.com/ (in English).
[51] OpenAI, “GPT-5.2,” 2026. [Online]. Available: https://openai.com/ (in English).

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 2026 Rastislav Metruk

