A Comparative Evaluation of Large Language Models in English-to-Chinese Translation of Energy-Domain Texts
Abstract
(LNG). The four main models to be compared are Deepseek, Zhipu Qingyan, Spark and Gemini. Some automatic quantitative indicators, such
as BLEU, BERTScore, COMET, GEMBA-MQM and human evaluation, have been used in this paper. Based on the above many indicators, all
of them have some strengths and weaknesses in different models. Based on the above results, the current LLMs cannot generate high-quality
translations independently in the special field of energy social science; therefore, to ensure the accuracy of the translation, a human-machine
collaboration model should be employed. In the future, more diverse kinds of corpora will be added to expand the above results.
Keywords
Full Text:
PDFReferences
[1] Sun, Y. (2026). A Study on Part-of-Speech Conversion in English-Chinese Translation of Petroleum Scientific and Technical Texts. Open
Access Library Journal, 13, e15610.
[2] Zhong, Q., & Tan, H. (2025). Research on Human Post-Editing Methods for Machine Translation of Petroleum Science and Technology
Texts. Journal of Language Service Studies, 1(2).
[3] Wang, L. (2023). The impacts and challenges of artificial intelligence translation tool on translation professionals. In SHS Web of Conferences (Vol. 163, p. 02021). EDP Sciences.
[4] Mohamed, Y. A., Khanan, A., Bashir, M., Mohamed, A. H. H., Adiel, M. A., & Elsadig, M. A. (2024). The impact of artificial intelligence on language translation: a review. IEEE access, 12, 25553-25579.
[5] Amini, M., Ravindran, L., & Lee, K. F. (2024). Implications of using AI in translation studies: Trends, challenges, and future direction.
Asian Journal of Research in Education and Social Sciences, 6(1), 740-754.
[6] Qing Zheng & Mansour Amini.(2026). Exploring the Development of AI-Mediated Competence for Sustainable Translation and Interpreting Education: A Bibliometric Review. Journal of Language Teaching and Research, 17(5), 1561-1574.https://doi.org/10.17507/
JLTR.1705.03.
[7] Weihe Xue.(2026). The effects of AI-collaborative translation workshop on translation competence and learner engagement: an empirical study in a Chinese university translation course. Frontiers
[8] Said Faiq & Mai Zaki.(2026). A Comparative Assessment of ChatGPT, DeepSeek and Human Translations of Cultural References
in the Moroccan Novel For Bread Alone. Journal of Language Teaching and Research, 17(5), 1653-1661. https://doi.org/10.17507/
JLTR.1705.11.
[9] Psychology, 17, 1918404-1918404. https://doi.org/10.3389/FPSYG.2026.1918404. Misnah Mannahali & Agung Rinaldy Malik.(2026).
Exploring AI-Assisted Translation and Cognitive Load in L2 Learning: Evidence From Indonesian University Students. Journal of Language Teaching and Research, 17(5), 1883-1893.https://doi.org/10.17507/JLTR.1705.32.
[10] Irena Horvatić Bilić & Lucia Miškulin Saletović.(2026). AI-Assisted Translation in Teaching Language for Legal Profession. International Journal for the Semiotics of Law-Revue internationale de Sémiotique juridique, (prepublish), 1-19. https://doi.org/10.1007/
S11196-026-1056-10566-Y.
DOI: http://dx.doi.org/10.70711/neet.v4i10.10294
Refbacks
- There are currently no refbacks.
