Your browser does not support the PubReader view.
Go to this page to see a list of supporting browsers.
The Korean Association for the Study of English Language and Linguistics
[ Article ]
Korea Journal of English Language and Linguistics - Vol. 25, No. 0, pp.912-934
ISSN: 1598-1398 (Print) 2586-7474 (Online)
Print publication date 31 Jan 2025
Received 13 May 2025 Revised 10 Jun 2025 Accepted 27 Jun 2025
DOI: https://doi.org/10.15738/kjell.25..202507.912

Gender Ambiguity in Human and AI Translations: “That Person” in Concerning My Daughter

Jin Yim
Lecturer, Graduate School of Translation and Interpretation, Ewha Womans University 52 Ewhayeodae-gil, Seodaemun-gu, Seoul, Korea jy2812@gmail.com


© 2025 KASELL All rights reserved
This is an open-access article distributed under the terms of the Creative Commons License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Recent advances in large language models (LLMs) have sparked growing interest in applying AI to literary translation, despite ongoing concerns about accurately capturing subtle textual cues related to characters’ identities and relationships, and faithfully representing queer themes without distortion or cultural normalization. This study investigates whether prompt design can guide AI translation systems to handle gender ambiguity—a central feature of many queer literary texts—with greater fidelity and sensitivity. Using 183 sentences from the Korean queer novel Concerning My Daughter, the study compares human translations with AI outputs generated under three prompting conditions: zero-shot prompting, contextual instruction prompting, and meta prompting. Both qualitative and quantitative analyses, including BLEU, TER, and BERTScore evaluations, reveal that prompt-based strategies significantly improve translation quality and reduce gender misrepresentation. However, the findings also highlight the persistent challenges of maintaining narrative ambiguity through AI systems. By focusing on a linguistically and ideologically critical feature—gender-neutral reference forms—this study contributes to discussions at the intersection of translation studies, queer theory, and AI ethics. It underscores the potential of prompt engineering not only as a tool for performance optimization but also as a strategy for addressing ethical considerations in literary translation workflows.

Keywords:

MT, AI translation, literary translation, queer translation, gender ambiguity

References

  • Aguilar, D. H. 2021. Translating gender ambiguity in literatura: The case of Written on the Body. Skopos 12, 137-167.
  • Anthropic. 2024. Claude [Large language model]. Available online at https://www.anthropic.com/claude
  • Baer, B. J. 2020. Queer Theory and Translation Studies: Language, Politics, Desire (1st ed.). Routledge. [https://doi.org/10.4324/9781315514734-1]
  • Basaure, R., M. Contreras, A. Campana and M. Ahumada. 2020. Translation and gender in South America: The representation of South American women writers in an unequal cultural scenario. In L. von Flotow and H. Kamal, eds., The Routledge Handbook of Translation, Feminism and Gender, 83-92. Taylor & Francis. [https://doi.org/10.4324/9781315158938-8]
  • Démont, M. 2017. On three modes of translating queer literary texts. In B. J. Baer & K. Kaindl, eds., Queering Translation, Translating the Queer (1st ed.), 157-171. Routledge. [https://doi.org/10.4324/9781315505978-12]
  • Gao, Y., R. Wang and F. Hou. 2023. How to design translation prompts for ChatGPT: An empirical study. arXiv preprint arXiv:2304.02182, . [https://doi.org/10.1145/3700410.3702123]
  • Ghosh, S. and A. Caliskan. 2023. ChatGPT perpetuates gender bias in machine translation and ignores non-gendered pronouns: Findings across Bengali and five other low-resource languages. In Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society (AIES), 967-977. [https://doi.org/10.1145/3600211.3604672]
  • Google. 2024. Google Colaboratory [Online computing environment]. Available online at https://colab.research.google.com/
  • Google DeepMind. 2024. Gemini 2.5 Flash [Large language model]. Available online at https://deepmind.google/gemini
  • Gu, W. 2023. Linguistically informed ChatGPT prompts to enhance Japanese-Chinese machine translation: A case study on attributive clauses. arXiv preprint arXiv:2303.15587
  • Guerberof-Arenas, A. and A. Toral. 2022. Creativity in translation: Machine translation as a constraint for literary texts. Translation Spaces 11(2), 184-212. [https://doi.org/10.1075/ts.21025.gue]
  • Hadley, J. L. 2023. MT and CAT: Challenges, irrelevancies, or opportunities for literary translation? In A. Ruthwell, A. Way, and R. Youdale, eds., Computer-Assisted Literary Translation (1st ed.), 91-105. Routledge. [https://doi.org/10.4324/9781003357391-7]
  • Hall, E. T. 1976. Beyond culture. Anchor.
  • Han, N.-R. 2006. Korean Zero Pronouns: Analysis and Resolution. Doctoral dissertation, University of Pennsylvania.
  • He, S. 2024. Prompting ChatGPT for translation: A comparative analysis of translation brief and persona prompts. arXiv preprint arXiv:2403.00127, .
  • Huang, C.-T. J. 1984. On the distribution and reference of empty pronouns. Linguistic Inquiry 15(4), 531-574.
  • Jagose, A. 1996. Queer Theory: An Introduction (Reprinted). New York University Press.
  • Jiao, W., W. Wang, J. Huang, X. Wang and Z. Tu. 2023. Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv preprint arXiv:2301.08745
  • Jiao, H., B. Peng, L. Zong, X. Zhang and X. Li. 2024. Gradable ChatGPT translation evaluation. arXiv preprint arXiv:2401.09984
  • Kenny, D. and M. Winters. 2020. Machine translation, ethics and the literary translator’s voice. Translation Spaces 9(1), 123-149. [https://doi.org/10.1075/ts.00024.ken]
  • Kim, H.-J. 2017. Concerning My Daughter. Minumsa.
  • Kim, H.-J. 2022. Concerning My Daughter (Translated by J. Chang). Picador.
  • Kocmi, T., C. Federmann, R. Grundkiewicz, M. Junczys-Dowmunt, H. Matsushita and A. Menezes. 2021. To ship or not to ship: An extensive evaluation of automatic metrics for machine translation. arXiv preprint arXiv:2107.10821, .
  • Lauscher, A., D. Nozza, A. Crowley, E. Miltersen and D. Hovy. 2023. What about “em”? How commercial machine translation fails to handle neo-pronouns. In Proceedings of the 61st Annual Meeting of the ACL, 333-348. [https://doi.org/10.18653/v1/2023.acl-long.23]
  • Lee, M. 2022. Translating gender indeterminacy: The queering of gender identities in Qiu Miaojin’s Last Words from Montmartre. Translation Studies 15(1), 54-68. [https://doi.org/10.1080/14781700.2021.1977687]
  • Liu, C., S.-E. Jhang, H. Park and H. Hahm. 2024. A corpus-based multilingual comparison of AI-based machine translations. Korea Journal of English Language and Linguistics 24, 257-276. [https://doi.org/10.15738/kjell.24..202404.257]
  • Love, H. 2009. Feeling Backward: Loss and the Politics of Queer History (First Harvard University Press paperback ed.). Harvard University Press. [https://doi.org/10.2307/j.ctvjghxr0]
  • Manapbayeva, Z., G. Zaurbekova, K. Ayazbekova, A. Kazezova and K. Pirmanova. 2024. AI in literary translation: ChatGPT-4 vs. professional human translation of Abai’s poem ‘Spring.’ Procedia Computer Science 251, 526–531. [https://doi.org/10.1016/j.procs.2024.11.143]
  • McPherson-Joseph, D. 2022, September–October. Concerning my daughter. Foreword Interviews 25(5), 62. https://link.gale.com/apps/doc/A747715712/LitRC?u=anon~1d65432e&sid=googleScholar&xid=c392a6ea
  • Miletich, M. 2012. Reading Gender in Translation: Translator’s Intervention in Isaac Chocrón’s Pronombres Personales. Doctoral dissertation, State University of New York at Binghamton.
  • Moorkens, J., A. Toral, S. Castilho and A. Way. 2018. Translators’ perceptions of literary post-editing using statistical and neural machine translation. Translation Spaces 7(2), 240-262. [https://doi.org/10.1075/ts.18014.moo]
  • OpenAI. 2024. ChatGPT-4o [Large language model]. Available online at https://openai.com/chatgpt
  • Papineni, K., S. Roukos, T. Ward and W.-J. Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of ACL-2002: 40th Annual Meeting of the Association for Computational Linguistics, 311–318. [https://doi.org/10.3115/1073083.1073135]
  • Peng, K., L. Ding, Q. Zhong, L. Shen, X. Liu, M. Zhang, Y. Ouyang and D. Tao. 2023. Towards making the most of ChatGPT for machine translation. SSRN Electronic Journal. [https://doi.org/10.2139/ssrn.4390455]
  • Perplexity AI. 2024. Perplexity AI Assistant [Large language model]. Available online at https://www.perplexity.ai
  • Prates, M. O. R., P. H. C. Avelar and L. Lamb. 2019. Assessing gender bias in machine translation—A case study with Google Translate. arXiv preprint arXiv: 1809.02208, .
  • Python Software Foundation. 2023. Python (Version 3.10) [Programming language]. Available online at https://www.python.org/
  • Rudan, S. M., E. Kelbert, L. Kovacevic, M. Reynolds and S. Rudan. 2023. Augmenting and informing the translation process through workflow-enabled CALT tools. In A. Rothwell, A. Way and R. Youdale, eds., Computer-assisted Literary Translation (1st ed.), 258-281. Routledge. [https://doi.org/10.4324/9781003357391-19]
  • Ruffo, P. 2022. Collecting literary translators’ narratives: Towards a new paradigm for technological innovation in literary translation. In J. L., Hadley K. Taivalkoski-Shilov, C. S. C. Teixeira and A. Toral, eds., Using Technologies for Creative-text Translation (1st ed.), 18-39. Routledge. [https://doi.org/10.4324/9781003094159-2]
  • Saunders, D. and K. Olsen. 2023. Gender, names and other mysteries: Towards the ambiguous for gender-inclusive translation. arXiv preprint arXiv:2306.04573
  • Saunders, D., R. Sallis, and B. Byrne. 2022. First the worst: Finding better gender translations during beam search. Findings of the Association for Computational Linguistics: ACL 2022, 3814–3823. [https://doi.org/10.18653/v1/2022.findings-acl.301]
  • Savoldi, B., M. Gaido, L. Bentivogli, M. Negri and M. Turchi. 2021. Gender bias in machine translation. Transactions of the Association for Computational Linguistics 9, 845-874. [https://doi.org/10.1162/tacl_a_00401]
  • Savoldi, B., E. Cupin, M. Thind, A. Lauscher, A. Piergentili, M. Negri and L. Bentivogli. 2025. mGeNTE: A multilingual resource for gender-neutral language and translation. arXiv preprint arXiv:2501.09409, .
  • Snover, M., B. Dorr, R. Schwartz, L. Micciulla and J. Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, 223-231.
  • Spallaccia, B. 2022. Queering the gender binary: American trans-themed YA literature and its translation into Italian. LINGUE CULTURE MEDIAZIONI, 69-87. [https://doi.org/10.7359/997-2022-bspa]
  • Spurlin, W. J. 2014. The gender and queer politics of translation: New approaches. Comparative Literature Studies 51(2), 201-214. [https://doi.org/10.5325/complitstudies.51.2.0201]
  • Suzgun, M. and A. T. Kalai. 2024. Meta-prompting: Enhancing language models with task-agnostic scaffolding. arXiv preprint arXiv:2401.12954, .
  • Tang, L., J. Qin, W. Ye, H. Tan and Z. Yang. 2025. Adaptive few-shot prompting for machine translation with pre-trained language models. arXiv preprint arXiv:2501.01679, . [https://doi.org/10.1609/aaai.v39i24.34712]
  • Vanmassenhove, E., C. Hardmeier and A. Way. 2018. Getting gender right in neural machine translation. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 3003-3008. [https://doi.org/10.18653/v1/D18-1334]
  • Vanmassenhove, E. 2024. Gender bias in machine translation and the era of large language models. arXiv preprint arXiv:2401.10016, . [https://doi.org/10.4324/9781003465508-12]
  • Wang, J., B. Rubinstein and T. Cohn. 2022. Measuring and mitigating name biases in neural machine translation. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2576-2590. [https://doi.org/10.18653/v1/2022.acl-long.184]
  • Webster, K., M. Recasens, V. Axelrod and J. Baldridge. 2018. Mind the gap: A balanced corpus of gendered ambiguous pronouns. Transactions of the Association for Computational Linguistics 6, 605–617. [https://doi.org/10.1162/tacl_a_00240]
  • Wu, M., Y. Yuan, G. Haffari and L. Wang. 2024. (Perhaps) beyond human translation: Harnessing multi-agent collaboration for translating ultra-long literary text. arXiv preprint arXiv:2405.11804
  • Xu, H., Y. J. Kim, A. Sharaf and H. H. Awadalla. 2024. A paradigm shift in machine translation: Boosting translation performance of large language models. arXiv preprint arXiv:2309.11674, .
  • Yan, J., P. Yan, Y. Chen, J. Li, X. Zhu and Y. Zhang. 2024. GPT-4 vs. human translators: A comprehensive evaluation of translation quality across languages, domains, and expertise levels. arXiv preprint arXiv: 2407.03658
  • Zhang, T., V. Kishore, F. Wu, K. Q. Weinberger and Y. Artzi. 2019. BertScore: Evaluating text generation with BERT. arXiv preprint arXiv:1904.09675, .
  • Zhang, R., W. Zhao and S. Eger. 2025. How good are LLMs for literary translation, really? Literary translation evaluation with humans and LLMs. arXiv preprint arXiv:1904.0967, . [https://doi.org/10.18653/v1/2025.naacl-long.548]