LLMs Aid Specialized Translation, But Can't Replace Corpora Yet

Joachim Minder (ALTAE), Guillaume Wisniewski (LLF - UMR7110), Natalie K\"ubler (ALTAE)· July 29, 2026 View original

Summary

A study evaluates LLMs like GPT-4o and Claude Sonnet 4.5 for specialized terminology translation from English to French. While useful, LLMs cannot fully replace specialized corpora, with performance varying by model, prompting strategy, and domain.

New research explores the utility of large language models (LLMs) in assisting specialized translators with terminology. The study investigates whether LLMs can serve as a viable alternative to traditional terminological resources like corpora, which are often time-consuming and technically demanding to compile. Four proprietary LLMs—GPT-4o, GPT-5.2, Claude Sonnet 4.5, and DeepSeek—were tested on 80 terms across Earth, Environmental and Planetary Sciences (EEPS) and Natural Language Processing (NLP) domains. Two prompting strategies, terminology mode and translation mode, were compared for English-to-French translation. Results showed notable differences among models, prompting strategies, and to a lesser extent, domains. Claude Sonnet 4.5 performed best in optimal configurations, while DeepSeek demonstrated greater stability. The study concludes that while LLMs are valuable tools for specialized translators, they are not yet capable of fully replacing specialized corpora, highlighting areas for future practical application and research.

Why it matters

Professionals in translation, content localization, and technical writing can leverage LLMs to enhance efficiency in finding specialized terminology, but must remain aware of their current limitations and the continued importance of curated domain-specific resources.

How to implement this in your domain

  1. 1Integrate LLM-based terminology assistance tools into specialized translation workflows.
  2. 2Experiment with different prompting strategies (e.g., terminology vs. translation mode) to optimize LLM output for specific domains.
  3. 3Cross-reference LLM-generated terminology with established specialized corpora or human experts for accuracy.
  4. 4Provide training to translators on effective LLM prompting and critical evaluation of AI-generated terms.
  5. 5Develop internal guidelines for when and how to best utilize LLMs alongside traditional terminological resources.

Who benefits

Translation ServicesTechnical WritingPublishingLegalHealthcare

Key takeaways

  • LLMs can assist specialized translators in finding terminology equivalents.
  • Performance varies significantly by model, prompting strategy, and domain.
  • Claude Sonnet 4.5 showed the best results in favorable conditions, DeepSeek offered stability.
  • LLMs are useful tools but cannot yet fully replace specialized corpora for accuracy.

Original post by Joachim Minder (ALTAE), Guillaume Wisniewski (LLF - UMR7110), Natalie K\"ubler (ALTAE)

"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:…"

View on X

Originally posted by Joachim Minder (ALTAE), Guillaume Wisniewski (LLF - UMR7110), Natalie K\"ubler (ALTAE) on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses