Using ChatGPT for evaluating students' translations

Evangelia Petridou

doi:10.24310/redit.20.2026.23685

Authors

Evangelia Petridou Ionian University Department of Foreign Languages Translation and Interpreting
Greece

DOI:

https://doi.org/10.24310/redit.20.2026.23685

Keywords:

Translation quality assessment, functional approach, GenAI, ChatGPT

Abstract

This study explores the reliability of Generative AI in Translation Quality Assessment in translator training settings. Eight anonymous translations from an undergraduate English into Greek translation course at Ionian University were assessed both by the instructor and GPT-5.0. To identify errors and score the translations, ChatGPT was prompted with the same rubric as that of the instructor. The instructor’s and the system’s assessments were compared to pinpoint any discrepancies. Results indicate that while ChatGPT can identify syntactic and grammatical errors, it is not always consistent when it comes to the assessment of errors regarding culturally-bound references. Thus, although GenAI might be a useful assessment tool, it cannot yet fully replace the instructor, whose oversight remains essential.

Downloads

Download data is not yet available.

References

Adab, B. 2000. “Evaluating translation competence”. En Schäffner, Christina and Beverly Adab (eds) Developing Translation Competence, Amsterdam and Philadelphia: John Benjamins, 215–228.

Akan, M. D. 2023. “Impact Of Artificial Intelligence (Ai) On Translation Quality: Assessment And Evaluation”. En Journal Of Southwest Jiaotong University.

Aleessawi, T. 2026. “The media and translation in the digital and AI era”. Applied Science Private University.

Alghamdi, F.A. y Alotaibi, H. 2025. “Using AI in Translation Quality Assessment: A Case Study of ChatGPT and Legal Translation Texts”. En Electronics, 14, 3893. https://doi.org/10.3390/electronics14193893

Arango-Keeth, F. and Koby, G. S. 2003. “Assessing assessment Translator training evaluation and the needs of industry quality assessment”. En Baer, Brian J. and Koby, G. S. (eds.) Beyond the Ivory Tower Rethinking translation pedagogy, Amsterdam and Philadelphia: John Benjamins, 117-134.

Dorri, E. R. 2018. “On the study of creativity in translation: The case study of journalistic text”. En Translation Journal. [consulta: 30 de marzo de 2026]. https://translationjournal.net/July-2018/on-the-study-of-creativity-in-translation-the-case-study-of-journalistic-text.html

Elmgrab, R. 2014. “Possible criteria for evaluating students’ translation errors”. En International Journal of Humanities and Cultural Studies, Vol. 1, Issue 3: 131–145.

Gonzalez-Davies, M. 2004. Multiple Voices in the Translation Classroom: Activities, tasks and projects. Amsterdam and Philadelphia: John Benjamins.

Reiss, K. y Vermeer, H. J. 2013. “Towards a General Theory of Translational Action: Skopos Theory Explained”. Contributed by Christiane Nord. London: Routledge.

Roe, J., Perkins, M., y Furze, L. 2026. “Applying the AI assessment scale in writing and translation for EFL”. En Artificial Intelligence in Education, 2(2), 59–74. https://doi.org/10.1108/AIIE-02-2025-0034

Williams, M. 2013. “A holistic-componential model for assessing translation student performance and competency”. En Mutatis Mutandis, 6(2): 419–443.

Xu, J. & Li, Y. 2026. “Generative AI in C-E translation of The Roots of Wisdom: A comparative study with human translations”. En Frontiers in Humanities and Social Sciences, Vol. 6, Issue 2.