On the Use of LLMs for Specialised Terminology: A Good Alternative to Corpora?

AI 中文解读

最新研究测试了GPT-4o、DeepSeek等顶尖大模型在专业术语翻译中的表现——结果发现它们能帮上忙，但暂时还干不过传统语料库。翻译专业术语时，过去得翻箱倒柜找一堆专业文档（语料库），费时又费力。现在研究人员尝试直接让AI聊天机器人“干活”：让它们把地球科学和自然语言处理领域的英文术语翻成法文，用了两种不同问法（术语模式或翻译模式）。结果显示，Claude Sonnet 4.5在某些设置下表现最好，DeepSeek则最稳定。不过AI自己给的“信心指数”只能部分反映翻译准不准，有时它信誓旦旦，结果却翻错了。对普通人来说，如果你是个专业翻译，可以用AI快速粗翻术语，省下不少查资料的时间，但重要场合最好还是翻翻专业文献核对一下。企业做多语言产品时，也能借助AI提速，但关键术语仍需人工把关。总体来说，这扇门已经推开了一半——未来AI会越来越靠谱，但现在还不是完全放手的时候。

arXiv:2607.24784v1 Announce Type: new Abstract: Specialised translation relies on the use of documentary and terminological resources, including corpora. These resources are particularly useful for terminology. However, their compilation and exploitation have several limitations: they require time, technical skills and access to data that can be difficult to collect. This study examines the extent to which LLMs can assist specialised translators in finding equivalents from English to French. We evaluate four proprietary models, GPT-4o, GPT-5.2, Claude Sonnet 4.5 and DeepSeek, in two specialised domains, Earth, Environmental and Planetary Sciences (EEPS) and Natural Language Processing (NLP). The experiment is based on 80 terms per domain and compares two prompting strategies: a terminology and a translation mode. The results highlight clear differences between models, prompting strategies and, to a lesser extent, domains. Claude Sonnet 4.5 achieves the best results in the most favourable configuration, while DeepSeek stands out for its greater stability. Analysis of confidence estimates also shows that they are only a partial indicator of terminological accuracy. Overall, the findings suggest that LLMs can be useful tools for specialised translators, but cannot, at this stage, replace specialised corpora. This research therefore paves the way for future work on the real practical usefulness of LLMs for specialised translators in work and educational contexts.