The Impact of Calibrated AI-Prompts on Translation Quality:
Insights from Cognitive Modifiability Perspectives
Abstract
This study investigated whether AI prompts calibrated to learners’ zones of proximal development (ZPD) improve translation quality more effectively than unguided AI assistance or conventional teacher feedback. Using a sequential mixed-methods, quasi-experimental design with 32 Iranian undergraduate translation students, a qualitative diagnostic phase identified four error types (lexico-semantic, syntactic-grammatical, pragmatic, meta-functional) and produced a ZPD-calibrated mediational inventory of graduated implicit-to-explicit prompts. In the quantitative phase, participants were assigned to three conditions: ZPD-tuned AI mediation (ChatGPT with calibrated prompts), normative AI mediation (standard ChatGPT use), or teacher feedback. One-way ANOVA showed a significant effect of mediation type, F (2, 29) = 33.574, p<.001. The ZPD-tuned AI group significantly outperformed both the normative AI group (MD = 5.15, p<.001) and the teacher feedback group (MD = 4.79, p<.001), with no significant difference between the latter two. Findings indicate that developmentally calibrated, scaffolded AI prompts produce superior translation outcomes compared to unguided AI access or conventional instruction, highlighting the value of integrating ZPD-aware prompt engineering into translator education.
Keywords:
AI-mediated translation, Cognitive modifiability, Mediation, Prompt engineering, Translation qualityReferences
Aljaafreh, A., & Lantolf, J. P. (1994). Negative feedback as regulation and second language learning in the zone of proximal development. Modern Language Journal, 78(4), 465–483. https://doi.org/10.2307/328585.
Farokhipour, S. (2019). Developing a local model of dynamic assessment for diagnosing problems and promoting English language skills in Iranian context (Unpublished doctoral dissertation). Chabahar Maritime University.
Farokhipour, S. (2025). Constructivist vs. positive psychology on learning: Developing a positive intervention inventory to mediate speaking, anxiety, and engagement. Iranian Journal of English for Academic Purposes, 14(2), 1–18.
Farokhipour, S., Khoshsima, H., Sarani, A., & Ganji, M. (2020). Presenting and investigating the effect of a local model of dynamic assessment in diagnosing and removing learning difficulties of high school students in productive skills. Journal of Foreign Language Research, 10(1), 120–134. https://doi.org/10.22059/jflr.2019.273144.593
Farokhipour, S., Padiz, D., & Hekmatshoartabari, B. (2025). Investigating the accuracy of GPT’s translation in transferring syntax–semantic interface: A case study of ideational meta-functions in English translation of Quran. Language Research, 16(1), 141–166. https://doi.org/10.22059/jolr.2025.391037.666912
Feuerstein, R., Falik, L., & Rand, Y. (2002). The dynamic assessment of cognitive modifiability. ICELP Press.
Gao, Y., Wang, R., & Hou, F. (2023). How to design translation prompts for ChatGPT: An empirical study. arXiv. https://arxiv.org/abs/2304.02182
Jiao, H., Peng, B., Zong, L., Zhang, X., & Li, X. (2024). Gradable ChatGPT translation evaluation. arXiv. https://arxiv.org/abs/2401.09984
Khosravani, M., Farokhipour, S., Padiz, D., & Hekmatshoartabari, B. (2025). A comparison of AI-assisted, AI-revised and human-scaffolded translations in ESP classes. Translation and Interpreting Research, 2(5), 45–58. https://doi.org/10.22054/tir.2025.86625.1044
Lantolf, J. P., & Poehner, M. E. (2010). Dynamic assessment in the classroom: Vygotskian praxis for second language development. Language Teaching Research, 15(1), 11–33. https://doi.org/10.1177/1362168810383328
Liang, L., & Lu, S. (2025). The evaluation and reception of the translation quality of three translation modalities in live-streaming contexts: Computer-assisted simultaneous interpreting, machine translation (MT) with human revision and raw MT. The Translator. Advance online publication. https://doi.org/10.1080/13556509.2025.2494566
Lidz, C. S. (1991). Practitioner’s guide to dynamic assessment. Guilford Press.
Mondshine, I., Paz-Argaman, T., & Tsarfaty, R. (2025). Beyond English: The impact of prompt translation strategies across languages and tasks in multilingual LLMs. Findings of the Association for Computational Linguistics: NAACL 2025, 1331–1354. https://doi.org/10.18653/v1/2025.findings-naacl.73
Mohsen, M., Althebi, S., & Albahooth, M. (2023). A scientometric study of three decades of machine translation research: Trending issues, hotspot research, and co-citation analysis. Cogent Arts & Humanities, 10(1). https://doi.org/10.1080/23311983.2023.2242620
Poehner, M. E. (2005). Dynamic assessment of oral proficiency among advanced L2 learners of French (Doctoral dissertation). Pennsylvania State University.
Poehner, M. E. (2008). Dynamic assessment: A Vygotskian approach to understanding and promoting L2 development. Springer.
Poehner, M. E., & van Compernolle, R. A. (2011). Frames of interaction in dynamic assessment: Developmental diagnoses of second language learning. Assessment in Education: Principles, Policy & Practice, 18(2), 183–198. https://doi.org/10.1080/0969594X.2011.567116
Saeedi, Z., & Soltani, M. (2025). Developing an AI chatbot for language pragmatics instruction: From algorithms to dynamic assessment in an EFL context. Computer Assisted Language Learning, 1–22. https://doi.org/10.1080/09588221.2025.2532014
Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.
Wang, H., & Zhang, J. Z. (2025). Translation practice models in the GenAI era: Technology iteration, business format change, and trend prospect. Journal of Foreign Language Teaching, 46(1), 53–58. https://doi.org/10.16362/j.cnki.cn61-1023/h.2025.01.011
Wu, G., & Ding, Z. (2025). An exploration of the linguistic features of translations generated by large language models: An investigation based on average dependency distance and its correlation with translation quality. Journal of Foreign Languages, 3, 48–55.
Zhang, J., & Doherty, S. (2025). Investigating novice translation students’ AI literacy in translation education. The Interpreter and Translator Trainer, 19(3–4), 234–253. https://doi.org/10.1080/1750399X.2025.2541478
Zhang, Y., & Fan, C. (2025). The impact of prompt strategies on specialized text translation by large language models: An empirical study using ChatGPT. In Proceedings of the 2025 International Conference on Educational Technology and Artificial Intelligence (pp. 218–222). https://doi.org/10.1145/3766557.3766594
Downloads
Published
How to Cite
Issue
Section
DOR
License
Copyright (c) 2026 Mahboobeh Khosravani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright Licensee: Iranian Journal of Translation Studies. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution–NonCommercial 4.0 International (CC BY-NC 4.0 license).
