JHASS

Article http://dx.doi.org/10.26855/jhass.2026.09.022

Prompt Engineering for Aviation Translation: An Evaluation of E-C LLM Output

Download PDF How to cite this paper

TOTAL VIEWS: 365

Weiwei Liu^*, Yiyang Tan, Yuanyuan Zhang

School of Foreign Languages, Civil Aviation Flight University of China, Chengdu 641419, Sichuan, China.

*Corresponding author: Weiwei Liu

This work was supported by “the Fundamental Research Funds for the Central Universities” (25CAFUC03077).

Published: September 28,2026

Abstract

Prompt design has become a practical concern in specialized translation with the increasingly widespread use of large language models. This study systematically examines how three prompt types affect English-Chinese translation quality in aviation texts: a basic translation instruction, a professional role instruction, and a context-based prompt with terminology guidance. The test material was carefully selected from an aviation article and comprehensively evaluated against a Chinese reference translation. The evaluation combines character-level reference similarity, edit-rate analysis, and aviation-oriented checks for terminology, entities, numbers, and cockpit-control labels. The comparison carefully shows that the prompt with the strongest surface similarity is not necessarily the one with the best domain accuracy. Terminology guidance significantly improved consistency in aviation expressions even when reference-overlap scores did not reach the highest value. The study strongly suggests that effective prompt engineering for aviation translation should combine clear task instructions, explicit domain constraints, and translator verification.

Keywords

Prompt engineering; aviation translation; specialized translation; large language models; translation quality

References

Airbus. (2023). Cockpit control confusion. Safety First.
https://safetyfirst.airbus.com/cockpit-control-confusion/

Freitag, M., Mathur, N., Deutsch, D., Lo, C.-K., Avramidis, E., Rei, R., Thompson, B., Blain, F., Kocmi, T., Wang, J., Ade-lani, D. I., Buchicchio, M., Zerva, C., & Lavie, A. (2024). Are LLMs breaking MT metrics? Results of the WMT24 metrics shared task. In Proceedings of the Ninth Conference on Machine Translation (pp. 47-81). Association for Computational Linguistics.
https://doi.org/10.18653/v1/2024.wmt-1.2

Gao, Y., Wang, R., & Hou, F. (2023). How to design translation prompts for ChatGPT: An empirical study. arXiv.

https://doi.org/10.48550/arXiv.2304.02182

Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y. J., Afify, M., & Awadalla, H. H. (2023). How good are GPT models at machine translation? A comprehensive evaluation. arXiv.

https://doi.org/10.48550/arXiv.2302.09210

Hu, J., & Fan, W. (2026). Prompt-engineering-based large language model translation practice: Characteristics, predicaments, and countermeasures. Foreign Languages in China, 23(2), 90-96.

https://doi.org/10.13564/j.cnki.issn.1672-9382.2026.02.011

Jiao, W., Wang, W., Huang, J.-T., Wang, X., Shi, S., & Tu, Z. (2023). Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv.
https://doi.org/10.48550/arXiv.2301.08745

Liu, W., Yu, C., & Gong, Y. (2025). Evaluating and improving LLM-based translation in aviation contexts. Journal of Humanities, Arts and Social Science, 9(8), 1664-1669.
https://doi.org/10.26855/jhass.2025.08.028

Yamada, M. (2023). Optimizing machine translation through prompt engineering: An investigation into ChatGPT’s cus-tomizability. In M. Yamada & F. do Carmo (Eds.), Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track (pp. 195-204). Asia-Pacific Association for Machine Translation.

https://aclanthology.org/2023.mtsummit-users.19/

Zhang, B., Haddow, B., & Birch, A. (2023). Prompting large language model for machine translation: A case study. arXiv.

https://doi.org/10.48550/arXiv.2301.07069

Zheng, J., Hong, H., Liu, F., Wang, X., Su, J., Liang, Y., & Wu, S. (2024). Fine-tuning large language models for domain-specific machine translation. arXiv.
https://doi.org/10.48550/arXiv.2402.15061

How to cite this paper

Prompt Engineering for Aviation Translation: An Evaluation of E-C LLM Output

How to cite this paper: Weiwei Liu, Yiyang Tan, Yuanyuan Zhang. (2026) Prompt Engineering for Aviation Translation: An Evaluation of E-C LLM Output. Journal of Humanities, Arts and Social Science, 10(9), 1173-1177.

DOI: http://dx.doi.org/10.26855/jhass.2026.09.022