AI 페르소나가 문학 번역에 미치는 영향 - 챗GPT 프롬프트에 따른 번역 사례 비교·분석The Impact of AI Persona on Literary Translation: A Case Analysis via ChatGPT Prompt Engineering
- Other Titles
- The Impact of AI Persona on Literary Translation: A Case Analysis via ChatGPT Prompt Engineering
- Authors
- 마승혜
- Issue Date
- Nov-2025
- Publisher
- 한국외국어대학교 통번역연구소
- Keywords
- AI literary translation; prompt engineering; persona; habitus; translation strategy; AI 문학 번역; 프롬프트 엔지니어링; 페르소나; 아비투스; 번역 전략
- Citation
- 통번역학연구, v.29, no.4, pp 1 - 35
- Pages
- 35
- Indexed
- KCI
- Journal Title
- 통번역학연구
- Volume
- 29
- Number
- 4
- Start Page
- 1
- End Page
- 35
- URI
- https://scholarworks.dongguk.edu/handle/sw.dongguk/62289
- DOI
- 10.22844/its.2025.29.4.1
- ISSN
- 1975-6321
2713-8372
- Abstract
- This study examines whether, when using the generative AI ChatGPT for literary translation, training it in specific habitus and strategies to construct a translator persona enables the model to move beyond its tendency toward literal translation and instead produce creative renderings aligned with that persona. To explore this, the paper focuses on Deborah Smith’s controversial translation of The Vegetarian, which sparked debate for employing a distinct habitus and feminist translation strategies that produced a work differing noticeably from the original. Before the habitus and strategy training, ChatGPT adhered closely to the source text in its translations; after the training, however, it generated outputs that diverged from the original according to the specific strategies, and these results were found not to differ significantly from Smith’s translation. In addition, by investigating and applying prompt-design techniques, this study explores ways to employ AI as an IA tool for literary translation.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Humanities > Division of English Language & Literature > 1. Journal Articles

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.