arXiv：cs.CL· Nune Ayvazan, Anthony Pym, Yu Hao·· 6 小时前AI 评分35
生成式 AI 翻译用于高风险应急信息
Generative AI translations in high-stakes emergency messaging
AI 导读
一项针对地震应急指令英译中、英译西的实验显示，使用契合话语场景的提示词（discourse-specific prompts）可显著提升生成式 AI 译文的可理解性和可操作性，但译者仍可能不信任这些译文。研究指出，人工修订依然必要，既为发现错误，也因为这类信息出错或延误需要有具体的人承担责任。
正文
Abstract:Emergency messaging such as extreme-weather reports and earthquake instructions can involve high stakes, to the extent that translation errors can lead to tragic consequences. The use of machine translation or generative artificial intelligence might therefore not be recommended. On the other hand, time savings in the initial translation can allow greater investments of resources in revision and authorization processes, as well as a wider range of target languages. An experiment with generative AI translations of an earthquake instruction text from English into Chinese and Spanish shows that use of discourse-specific prompts can considerably improve understandability and actionability, although the translations may still not be trusted by translators. Human revision is still required, not only to detect errors but also because of the ethical need for someone to take responsibility for any errors or delays in such messaging.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.08601 [cs.CL] |
| (or arXiv:2610.08601v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08601 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Anthony Pym [view email]
[v1]
Tue, 6 Oct 2026 16:06:22 UTC (837 KB)
来源：arXiv：cs.CL · arxiv.org