Article In: Humans, Machines, and Embedded Translation
Edited by Sandra L. Halverson and Jean Nitzke
[Translation, Cognition & Behavior 8:2] 2025
Prompting as thinking
Understanding the decisions made by translators in AI-assisted translation
This content is being prepared for publication; it may be subject to changes.
Abstract
This paper assesses AI-assisted translation by viewing prompting as an externalisation of cognitive processes
during translator-AI interaction. More than mere technical inputs, prompts serve as authentic written traces behind the
identification of problems by translators and their resultant solutions. This approach differs from traditional think-aloud
methods by offering explicit access to decision-making. Using screen recordings and think-aloud protocols, the study observes
seven trainee translators working on English-to-Chinese translation tasks using ChatGPT. The paper analyses three critical
decision points: (1) when outputs are accepted, (2) factors triggering prompt engineering, and (3) criteria leading translators to
stop prompting. Findings provide evidence-based insights for developing translator AI competence and inform a pedagogical
framework that highlights the visibility of prompting processes, thereby enhancing translator education in the AI era. [125
words]
Article outline
- 1.Introduction
- 2.Literature review
- 2.1Prompt engineering for translation-related tasks
- 2.2Prompting as information seeking
- 2.3Understanding prompting as a cognitive process
- 3.Research design
- 3.1Data
- 3.2Analytical framework
- 4.Results and discussion
- 4.1Conditions for desired outputs
- 4.2Triggers for prompt engineering
- 4.3Decision to stop prompting
- 4.3.1Efficiency optimisation stopping
- 4.3.2Goal achievement stopping
- 4.3.3Capability limitation stopping
- 4.4Pedagogical implications
- 4.5Limitations
- 5.Conclusion
- Author queries
References
References (75)
Agosto, Denise E. 2002. “Bounded rationality and
satisficing in young people’s Web-based decision making.” Journal of the American Society for
Information Science and
Technology 53(1): 16–27.
Aldosari, Lama Abdullah and Nasrin Altuwairesh. 2025. “Assessing
the effects of translation prompts on the translation quality of GPT-4 Turbo using automated and human evaluation metrics: a
case
study.” Perspectives: 1–25.
Alves, Fabio and José Luiz Gonçalves. 2013. “Investigating
the conceptual-procedural distinction in the translation process: A relevance-theoretic analysis of micro and macro
translation
units.” Target 25(1): 107–124.
Anthropic. n.d. “Use examples
(multishot prompting) to guide Claude’s behavior.” accessed Novermber 24. [URL]
AWS. n.d. “What is Prompt
Engineering?”, accessed July
25. [URL]
Bernardini, Silvia. 1999. “Using
Think-Aloud Protocols to Investigate the Translation Process: Methodological Aspects.” RCEAL
Working papers in English and applied
linguistics (6): 179–199.
. 2001. “Think-aloud
protocols in translation research: Achievements, limits, future prospects.” Target.
International Journal of Translation
Studies 13(2): 241–263.
Briva-Iglesias, Vicent, Joao Lucas Cavalheiro Camargo, and Gokhan Dogru. 2024. Large
Language Models “Ad Referendum”: How Good Are They at Machine Translation in the Legal Domain?.
Cooper, William S. 1973. “On selecting a measure of
retrieval effectiveness part II. Implementation of the philosophy.” Journal of the American
Society for Information
Science 24(6): 413–424.
Cui, Yixiao and Binghan Zheng. 2021. “Consultation
behaviour with online resources in English-Chinese translation: an eye-tracking, screen-recording and retrospective
study.” Perspectives 29(5): 740–760.
Dam-Jensen, Helle and Carmen Heine. 2009. “Process
Research Methods and Their Application in the Didactics of Text Production and
Translation.” trans-kom 2(1): 1–25.
Dong, Dahui and Meng-Lin Chen. 2025. “Metacognitive
strategies in translation: a comparative study of student and professional
translators.” Humanities and Social Sciences
Communications 12(1): 890.
Emirkadi, Ezginaz. 2023. “At
the Crossroads of Translation and Cognition: Tracing Decision Making in Translation through Think-Aloud
Protocol.” IU Journal of Translation
Studies (18): 215–232.
Enríquez Raído, Vanessa and Yuxing Cai. 2023. “Changes
in web search query behavior of English-to-Chinese translation
trainees.” Ampersand 11(100137.
Ericsson, K. Anders and Herbert A. Simon. 1993. Protocol
Analysis: Verbal Reports as Data: The MIT Press.
Freitag, Markus, George Foster, David Grangier, Viresh Ratnakar, Qijun Tan, and Wolfgang Macherey. 2021. “Experts,
Errors, and Context: A Large-Scale Study of Human Evaluation for Machine
Translation.” Transactions of the Association for Computational
Linguistics 9(1460–1474.
Gao, Yuan, Ruili Wang, and Feng Hou. 2024. “How
to Design Translation Prompts for ChatGPT: An Empirical Study.” Proceedings of the 6th ACM
International Conference on Multimedia in Asia Workshops.
Geroimenko, Vladimir. 2025. The
Essential Guide to Prompt Engineering: Key Principles, Techniques, Challenges, and Security
Risks. Cham, Switzerland: Springer.
Ginel, María Isabel Rivas and Joss Moorkens. 2025. “Translators’
trust and distrust in the times of GenAI.” Translation
Studies: 1–17.
Google. n.d. “Prompt design
strategies.” accessed November
24. [URL]
Göpferich, Susanne. 2009. “Towards
a model of translation competence and its acquisition: the longitudinal study
TransComp.” Copenhagen studies in
language: 11–37.
Gu, Wenshi. 2025. “Linguistically
informed ChatGPT prompts to enhance Japanese-Chinese machine translation: A case study on attributive
clauses.” PLOS
ONE 20(1): e0313264.
Guan, Xingzhong. 2024. “A
Bard is Born: A New Era of Poetry Translation by ChatGPT-4.” Translation
Review 120(1): 23–39.
Hadley, James Luke, Kristiina Taivalkoski-Shilov, Carlos S. C. Teixeira, and Antonio Toral. 2022. “Introduction.” In Using
Technologies for Creative-Text Translation, ed. by James Luke Hadley, Kristiina Taivalkoski-Shilov, Carlos S. C. Teixeira, and Antonio Toral, 1–17. New York: Routledge.
He, Sui. 2024. “Prompting
ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona
Prompts.” Sheffield, UK, June.
He, Zhiwei, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Yujiu Yang, Rui Wang, Zhaopeng Tu, Shuming Shi, and Xing Wang. 2024. “Exploring
Human-Like Translation Strategy with Large Language Models.” Transactions of the Association
for Computational Linguistics 12(229–246.
Hvelplund, Kristian Tangsgaard. 2017. “Translators’ Use of
Digital Resources during Translation.” HERMES — Journal of Language and Communication in
Business 0(56): 71–87.
. 2019. “Digital resources in
the translation process–attention, cognitive effort and processing
flow.” Perspectives 27(4): 510–524.
IBM. 2025. “The 2025 Guide to Prompt
Engineering.” accessed November
24. [URL]
Ilani, Fereshte, Mohsen Nowkarizi, and Sholeh Arastoopoor. 2024. “Analysis
of the factors affecting information search stopping behavior: A systematic review.” Journal of
Librarianship and Information
Science 56(3): 796–808.
Jääskeläinen, Riitta. 2002. “Think-aloud
protocol studies into translation: An annotated bibliography.” Target. International Journal of
Translation
Studies 14(1): 107–136.
. 2016. “Think-aloud
protocol.” In Handbook of Translation
Studies, ed. by Yves Gambier and Luc van Doorslaer, 371–373. John Benjamins.
Jiao, Wenxiang, Wenxuan Wang, Jen-tse Huang, Xing Wang, Shuming Shi, and Zhaopeng Tu. 2023. Is
ChatGPT A Good Translator? Yes With GPT-4 As The Engine. arXiv:2301.08745.
Accessed January 01, 2023.
Jiménez Crespo, Miguel Ángel. 2024. “Exploring professional
translators’ attitudes towards control and autonomy in the human-centred AI era: quantitative results from a survey
study.” Revista Tradumàtica: translation
technologies22): 276–301.
Jiménez-Crespo, Miguel A. 2024. “Transcreation in Translation
and the Age of Human-Centred AI: Focusing on “Human” Creative
Touch.” In New Perspectives in Media Translation: Transcreation in
the Digital Age, ed. by Loukia Kostopoulou and Parthena Charalampidou, 309–320. Cham: Springer International Publishing.
Krings, Hans-Peter. 1986. “Translation
problems and translation strategies of advanced German learners of French
(L2).” In Interlingual and intercultural communication: discourse and
cognition in translation and second language acquisition studies, ed. by Juliane House and Shoshana Blum-Kulka, 263–276. Tübingen: Gunter Narr.
Künzli, Alexander. 2009. “Think-aloud
Protocols — A Useful Tool for Investigating the Linguistic Aspect of
Translation.” Meta 54(2): 326–341.
Kuznik, Anna. 2017. “Use
of Instrumental Resources.” In Researching Translation Competence by
PACTE Group, ed. by Amparo Hurtado Albir, 219–242. Amsterdam: John Benjamins.
Kuznik, Anna and Christian Olalla-Soler. 2018. “Results
of PACTE group’s experimental research on translation competence acquisition. The acquisition of the instrumental
sub-competence.” Across Languages and
Cultures 19(1): 19–51.
Liu, Jiaxin. 2024. “ChatGPT:
perspectives from human-computer interaction and psychology.” Frontiers in Artificial
Intelligence 7(1418869.
López, Ana María Rojo and Ricardo Muñoz Martín. 2022. “Translation
process research.” In The Routledge Handbook of Translation and
Methodology, ed. by Federico Zanettin and Christopher Rundle, 356–372. London: Routledge.
Lörscher, Wolfgang. 1991. Translation
performance, translation process, and translation strategies: A psycholinguistic
investigation. Tübingen: Gunter Narr.
Lu, Qingyu, Baopu Qiu, Liang Ding, Kanjian Zhang, Tom Kocmi, and Dacheng Tao. 2024. “Error
Analysis Prompting Enables Human-Like Translation Evaluation in Large Language
Models.” Bangkok, Thailand, August.
Marchionini, Gary. 1995. Information
Seeking in Electronic Environments, Cambridge Series on Human-Computer
Interaction. Cambridge: Cambridge University Press.
Massey, Gary and Maureen Ehrensberger-Dow. 2011. “Investigating
information literacy: A growing priority in translation studies.” Across Languages and
Cultures 12(2): 193–211.
Moreno García, Luis Damián and Carme Mangiron. 2024. “Exploring
the potential of GPT-4 as an interactive transcreation assistant in game localisation: A case study on the translation of
Pokémon
names.” Perspectives: 1–18.
Munoz, Martin Ricardo and Christian Olalla-Soler. 2022. “Translating
is not (only) problem solving.” The Journal of Specialised
Translation (38): 3–31.
Njifenjou, Ahmed, Virgile Sucal, Bassam Jabaian, and Fabrice Lefèvre. 2024. Role-Play
Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine
Conversation. arXiv:2406.18460. Accessed June 01, 2024.
Oatley, Keith and Maja Djikic. 2008. “Writing
as thinking.” Review of General
Psychology 12(1): 9–27.
Olalla-Soler, Christian. 2018. “Using
electronic information resources to solve cultural translation problems: Differences between students and professional
translators.” Journal of
Documentation 74(6): 1293–1317.
OpenAI. 2022. “OpenAI: Introducing
ChatGPT.” [URL]
. n.d. “Best practices
for prompt engineering with the OpenAI API.” accessed November 24. [URL]
PACTE. 2011. “Results of the
validation of the PACTE translation competence model.” In Methods and
Strategies of Process Research: Integrative approaches in Translation Studies, ed.
by Cecilia Alvstad, Adelina Hild, and Elisabet Tiselius, 317–343. John Benjamins.
. 2014. “First Results of
PACTE Group’s Experimental Research on Translation Competence Acquisition: The Acquisition of Declarative Knowledge of
Translation.” MonTI : Monografías de Traducción e
Interpretación: 85–115.
. 2017. “PACTE Translation
Competence model: A holistic, dynamic model of Translation
Competence.” In Researching Translation Competence by PACTE
Group, ed. by Albir Amparo Hurtado, 35–42. John Benjamins Publishing Company.
Paris, LAH. 1988. “Stopping
behavior: User persistence in online searching and its relation to optimal cutoff points for information retrieval
systems.” PhD, Library and Information Science, University of North Carolina, Chapel Hill
Peng, Keqin, Liang Ding, Qihuang Zhong, Li Shen, Xuebo Liu, Min Zhang, Yuanxin Ouyang, and Dacheng Tao. 2023. “Towards
Making the Most of ChatGPT for Machine
Translation.” Singapore, December.
Pym, Anthony and Hao Yu. 2024. How
to Augment Language Skills: Generative AI and Machine Translation in Language Learning and Translator
Training: Routledge.
Sharkas, Hala. 2025. “Exploring
the Role of Translation Brief Elements in Prompts to Large Language Models.” AWEJ for
Translation & Literary
Studies 9(2): 139–153.
Shih, Claire Y. 2017. “Web search for translation: an
exploratory study on six Chinese trainee translators’ behaviour.” Asia Pacific Translation and
Intercultural
Studies 4(1): 50–66.
2019. “A quest for web search
optimisation: an evidence-based approach to trainee translators’
behaviour.” Perspectives 27(6): 908–923.
2021. “Navigating the Web: A Study on
Professional Translators’ Behaviour.” In Empirical Studies of
Translation and Interpreting: The Post-Structuralist Approach, ed. by Caiwen Wang and Binghan Zheng. New York: Routledge.
Sun, Sanjun. 2011. “Think-Aloud-Based
Translation Process Research: Some Methodological
Considerations.” Meta 56(4): 928–951.
Sunstein, Cass R. 2000. “Cognition And Cost-Benefit
Analysis.” The Journal of Legal
Studies 29(S2): 1059–1103.
Wang, Longyue, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, and Zhaopeng Tu. 2023. Document-Level
Machine Translation with Large Language
Models. arXiv:2304.02210. Accessed April 01, 2023.
Wang, Vincent X. and Lily Lim. 2017. “How
do translators use web resources? Evidence from the performance of English–Chinese
translators.” In Human Issues in Translation
Technology, ed. by Dorothy Kenny. London: Routledge.
Wu, Chenze, Hanqi Yu, Benjamin Luke Moorhouse, and Meixin Wu. 2025. “Unveiling
students’ experiences and perspectives of generative AI-assisted translation in a Hong Kong university: perceived benefits,
limitations, and suggestions.” Digital Applied
Linguistics 2(102600.
Wu, Wan-Ching and Diane Kelly. 2014. “Online
search stopping behaviors: An investigation of query abandonment and task
stopping.” Proceedings of the American Society for Information Science and
Technology 51(1): 1–10.
Yamada, Masaru. 2023. “Optimizing
Machine Translation through Prompt Engineering: An Investigation into ChatGPT‘s
Customizability.” Macau SAR, China, September.
Zhang, Chen, Xinyi Dai, Yaxiong Wu, Qu Yang, Yasheng Wang, Ruiming Tang, and Yong Liu. 2025. A
Survey on Multi-Turn Interaction Capabilities of Large Language
Models. arXiv:2501.09959. Accessed January 01, 2025.
Zhang, Min, Limin Liu, Zhao Yanqing, Xiaosong Qiao, Su Chang, Xiaofeng Zhao, Junhao Zhu, Ming Zhu, Song Peng, Yinglu Li, Yilun Liu, Wenbing Ma, Mengyao Piao, Shimin Tao, Hao Yang, and Yanfei Jiang. 2023. “Leveraging
Multilingual Knowledge Graph to Boost Domain-specific Entity Translation of
ChatGPT.” Macau SAR, China, September.
Zhang, Shuyin. in
press. “Investigating Translator-AI interaction: An Exploratory Study on Trainee Translators’
Prompt Engineering Behaviour.” In Translation Education in the Era of
Artificial Intelligence, ed. by Yingyi Zhuang, Shuyin Zhang, and Yuanyuan Mu. London: Routledge.
